Daily Papers

Recent language model (LM) advancements have showcased impressive zero-shot voice conversion (VC) performance. However, existing LM-based VC models usually apply offline conversion from source semantics to acoustic features, demanding the complete source speech, and limiting their deployment to real-time applications. In this paper, we introduce StreamVoice, a novel streaming LM-based model for zero-shot VC, facilitating real-time conversion given arbitrary speaker prompts and source speech. Specifically, to enable streaming capability, StreamVoice employs a fully causal context-aware LM with a temporal-independent acoustic predictor, while alternately processing semantic and acoustic features at each time step of autoregression which eliminates the dependence on complete source speech. To address the potential performance degradation from the incomplete context in streaming processing, we enhance the context-awareness of the LM through two strategies: 1) teacher-guided context foresight, using a teacher model to summarize the present and future semantic context during training to guide the model's forecasting for missing context; 2) semantic masking strategy, promoting acoustic prediction from preceding corrupted semantic and acoustic input, enhancing context-learning ability. Notably, StreamVoice is the first LM-based streaming zero-shot VC model without any future look-ahead. Experimental results demonstrate StreamVoice's streaming conversion capability while maintaining zero-shot performance comparable to non-streaming VC systems.

Recent advancements in audio generation have enabled the creation of high-fidelity audio clips from free-form textual descriptions. However, temporal relationships, a critical feature for audio content, are currently underrepresented in mainstream models, resulting in an imprecise temporal controllability. Specifically, users cannot accurately control the timestamps of sound events using free-form text. We acknowledge that a significant factor is the absence of high-quality, temporally-aligned audio-text datasets, which are essential for training models with temporal control. The more temporally-aligned the annotations, the better the models can understand the precise relationship between audio outputs and temporal textual prompts. Therefore, we present a strongly aligned audio-text dataset, AudioTime. It provides text annotations rich in temporal information such as timestamps, duration, frequency, and ordering, covering almost all aspects of temporal control. Additionally, we offer a comprehensive test set and evaluation metric to assess the temporal control performance of various models. Examples are available on the https://zeyuxie29.github.io/AudioTime/

Research on multi-modal contrastive learning strategies for audio and text has rapidly gained interest. Contrastively trained Audio-Language Models (ALMs), such as CLAP, which establish a unified representation across audio and language modalities, have enhanced the efficacy in various subsequent tasks by providing good text aligned audio encoders and vice versa. These improvements are evident in areas like zero-shot audio classification and audio retrieval, among others. However, the ability of these models to understand natural language and temporal relations is still a largely unexplored and open field for research. In this paper, we propose to equip the multi-modal ALMs with temporal understanding without loosing their inherent prior capabilities of audio-language tasks with a temporal instillation method TeminAL. We implement a two-stage training scheme TeminAL A & B, where the model first learns to differentiate between multiple sounds in TeminAL A, followed by a phase that instills a sense of time, thereby enhancing its temporal understanding in TeminAL B. This approach results in an average performance gain of 5.28% in temporal understanding on the ESC-50 dataset, while the model remains competitive in zero-shot retrieval and classification tasks on the AudioCap/Clotho datasets. We also note the lack of proper evaluation techniques for contrastive ALMs and propose a strategy for evaluating ALMs in zero-shot settings. The general-purpose zero-shot model evaluation strategy ZSTE, is used to evaluate various prior models. ZSTE demonstrates a general strategy to evaluate all ZS contrastive models. The model trained with TeminAL successfully outperforms current models on most downstream tasks.

Self-supervised speech representations have been shown to be effective in a variety of speech applications. However, existing representation learning methods generally rely on the autoregressive model and/or observed global dependencies while generating the representation. In this work, we propose Non-Autoregressive Predictive Coding (NPC), a self-supervised method, to learn a speech representation in a non-autoregressive manner by relying only on local dependencies of speech. NPC has a conceptually simple objective and can be implemented easily with the introduced Masked Convolution Blocks. NPC offers a significant speedup for inference since it is parallelizable in time and has a fixed inference time for each time step regardless of the input sequence length. We discuss and verify the effectiveness of NPC by theoretically and empirically comparing it with other methods. We show that the NPC representation is comparable to other methods in speech experiments on phonetic and speaker classification while being more efficient.

Zero-shot text-to-speech aims at synthesizing voices with unseen speech prompts. Previous large-scale multispeaker TTS models have successfully achieved this goal with an enrolled recording within 10 seconds. However, most of them are designed to utilize only short speech prompts. The limited information in short speech prompts significantly hinders the performance of fine-grained identity imitation. In this paper, we introduce Mega-TTS 2, a generic zero-shot multispeaker TTS model that is capable of synthesizing speech for unseen speakers with arbitrary-length prompts. Specifically, we 1) design a multi-reference timbre encoder to extract timbre information from multiple reference speeches; 2) and train a prosody language model with arbitrary-length speech prompts; With these designs, our model is suitable for prompts of different lengths, which extends the upper bound of speech quality for zero-shot text-to-speech. Besides arbitrary-length prompts, we introduce arbitrary-source prompts, which leverages the probabilities derived from multiple P-LLM outputs to produce expressive and controlled prosody. Furthermore, we propose a phoneme-level auto-regressive duration model to introduce in-context learning capabilities to duration modeling. Experiments demonstrate that our method could not only synthesize identity-preserving speech with a short prompt of an unseen speaker but also achieve improved performance with longer speech prompts. Audio samples can be found in https://mega-tts.github.io/mega2_demo/.

Contrastive language-audio pretraining~(CLAP) has been developed to align the representations of audio and language, achieving remarkable performance in retrieval and classification tasks. However, current CLAP struggles to capture temporal information within audio and text features, presenting substantial limitations for tasks such as audio retrieval and generation. To address this gap, we introduce T-CLAP, a temporal-enhanced CLAP model. We use Large Language Models~(LLMs) and mixed-up strategies to generate temporal-contrastive captions for audio clips from extensive audio-text datasets. Subsequently, a new temporal-focused contrastive loss is designed to fine-tune the CLAP model by incorporating these synthetic data. We conduct comprehensive experiments and analysis in multiple downstream tasks. T-CLAP shows improved capability in capturing the temporal relationship of sound events and outperforms state-of-the-art models by a significant margin.

Time-aligned lyrics can enrich the music listening experience by enabling karaoke, text-based song retrieval and intra-song navigation, and other applications. Compared to text-to-speech alignment, lyrics alignment remains highly challenging, despite many attempts to combine numerous sub-modules including vocal separation and detection in an effort to break down the problem. Furthermore, training required fine-grained annotations to be available in some form. Here, we present a novel system based on a modified Wave-U-Net architecture, which predicts character probabilities directly from raw audio using learnt multi-scale representations of the various signal components. There are no sub-modules whose interdependencies need to be optimized. Our training procedure is designed to work with weak, line-level annotations available in the real world. With a mean alignment error of 0.35s on a standard dataset our system outperforms the state-of-the-art by an order of magnitude.

Scaling Text-to-speech (TTS) to large-scale datasets has been demonstrated as an effective method for improving the diversity and naturalness of synthesized speech. At the high level, previous large-scale TTS models can be categorized into either Auto-regressive (AR) based (e.g., VALL-E) or Non-auto-regressive (NAR) based models (e.g., NaturalSpeech 2/3). Although these works demonstrate good performance, they still have potential weaknesses. For instance, AR-based models are plagued by unstable generation quality and slow generation speed; meanwhile, some NAR-based models need phoneme-level duration alignment information, thereby increasing the complexity of data pre-processing, model design, and loss design. In this work, we build upon our previous publication by implementing a simple and efficient non-autoregressive (NAR) TTS framework, termed SimpleSpeech 2. SimpleSpeech 2 effectively combines the strengths of both autoregressive (AR) and non-autoregressive (NAR) methods, offering the following key advantages: (1) simplified data preparation; (2) straightforward model and loss design; and (3) stable, high-quality generation performance with fast inference speed. Compared to our previous publication, we present ({\romannumeral1}) a detailed analysis of the influence of speech tokenizer and noisy label for TTS performance; ({\romannumeral2}) four distinct types of sentence duration predictors; ({\romannumeral3}) a novel flow-based scalar latent transformer diffusion model. With these improvement, we show a significant improvement in generation performance and generation speed compared to our previous work and other state-of-the-art (SOTA) large-scale TTS models. Furthermore, we show that SimpleSpeech 2 can be seamlessly extended to multilingual TTS by training it on multilingual speech datasets. Demos are available on: {https://dongchaoyang.top/SimpleSpeech2\_demo/}.

Lifelong audio feature extraction involves learning new sound classes incrementally, which is essential for adapting to new data distributions over time. However, optimizing the model only on new data can lead to catastrophic forgetting of previously learned tasks, which undermines the model's ability to perform well over the long term. This paper introduces a new approach to continual audio representation learning called DeCoR. Unlike other methods that store previous data, features, or models, DeCoR indirectly distills knowledge from an earlier model to the latest by predicting quantization indices from a delayed codebook. We demonstrate that DeCoR improves acoustic scene classification accuracy and integrates well with continual self-supervised representation learning. Our approach introduces minimal storage and computation overhead, making it a lightweight and efficient solution for continual learning.

The two most common paradigms for end-to-end speech recognition are connectionist temporal classification (CTC) and attention-based encoder-decoder (AED) models. It has been argued that the latter is better suited for learning an implicit language model. We test this hypothesis by measuring temporal context sensitivity and evaluate how the models perform when we constrain the amount of contextual information in the audio input. We find that the AED model is indeed more context sensitive, but that the gap can be closed by adding self-attention to the CTC model. Furthermore, the two models perform similarly when contextual information is constrained. Finally, in contrast to previous research, our results show that the CTC model is highly competitive on WSJ and LibriSpeech without the help of an external language model.

Several recent end-to-end text-to-speech (TTS) models enabling single-stage training and parallel sampling have been proposed, but their sample quality does not match that of two-stage TTS systems. In this work, we present a parallel end-to-end TTS method that generates more natural sounding audio than current two-stage models. Our method adopts variational inference augmented with normalizing flows and an adversarial training process, which improves the expressive power of generative modeling. We also propose a stochastic duration predictor to synthesize speech with diverse rhythms from input text. With the uncertainty modeling over latent variables and the stochastic duration predictor, our method expresses the natural one-to-many relationship in which a text input can be spoken in multiple ways with different pitches and rhythms. A subjective human evaluation (mean opinion score, or MOS) on the LJ Speech, a single speaker dataset, shows that our method outperforms the best publicly available TTS systems and achieves a MOS comparable to ground truth.

This paper makes several contributions to automatic lyrics transcription (ALT) research. Our main contribution is a novel variant of the Multistreaming Time-Delay Neural Network (MTDNN) architecture, called MSTRE-Net, which processes the temporal information using multiple streams in parallel with varying resolutions keeping the network more compact, and thus with a faster inference and an improved recognition rate than having identical TDNN streams. In addition, two novel preprocessing steps prior to training the acoustic model are proposed. First, we suggest using recordings from both monophonic and polyphonic domains during training the acoustic model. Second, we tag monophonic and polyphonic recordings with distinct labels for discriminating non-vocal silence and music instances during alignment. Moreover, we present a new test set with a considerably larger size and a higher musical variability compared to the existing datasets used in ALT literature, while maintaining the gender balance of the singers. Our best performing model sets the state-of-the-art in lyrics transcription by a large margin. For reproducibility, we publicly share the identifiers to retrieve the data used in this paper.

We propose TalkNet, a non-autoregressive convolutional neural model for speech synthesis with explicit pitch and duration prediction. The model consists of three feed-forward convolutional networks. The first network predicts grapheme durations. An input text is expanded by repeating each symbol according to the predicted duration. The second network predicts pitch value for every mel frame. The third network generates a mel-spectrogram from the expanded text conditioned on predicted pitch. All networks are based on 1D depth-wise separable convolutional architecture. The explicit duration prediction eliminates word skipping and repeating. The quality of the generated speech nearly matches the best auto-regressive models - TalkNet trained on the LJSpeech dataset got MOS 4.08. The model has only 13.2M parameters, almost 2x less than the present state-of-the-art text-to-speech models. The non-autoregressive architecture allows for fast training and inference. The small model size and fast inference make the TalkNet an attractive candidate for embedded speech synthesis.

Large-scale, weakly-supervised speech recognition models, such as Whisper, have demonstrated impressive results on speech recognition across domains and languages. However, their application to long audio transcription via buffered or sliding window approaches is prone to drifting, hallucination & repetition; and prohibits batched transcription due to their sequential nature. Further, timestamps corresponding each utterance are prone to inaccuracies and word-level timestamps are not available out-of-the-box. To overcome these challenges, we present WhisperX, a time-accurate speech recognition system with word-level timestamps utilising voice activity detection and forced phoneme alignment. In doing so, we demonstrate state-of-the-art performance on long-form transcription and word segmentation benchmarks. Additionally, we show that pre-segmenting audio with our proposed VAD Cut & Merge strategy improves transcription quality and enables a twelve-fold transcription speedup via batched inference.

In this paper we propose a novel model for unconditional audio generation based on generating one audio sample at a time. We show that our model, which profits from combining memory-less modules, namely autoregressive multilayer perceptrons, and stateful recurrent neural networks in a hierarchical structure is able to capture underlying sources of variations in the temporal sequences over very long time spans, on three datasets of different nature. Human evaluation on the generated samples indicate that our model is preferred over competing models. We also show how each component of the model contributes to the exhibited performance.

This paper describes Tacotron 2, a neural network architecture for speech synthesis directly from text. The system is composed of a recurrent sequence-to-sequence feature prediction network that maps character embeddings to mel-scale spectrograms, followed by a modified WaveNet model acting as a vocoder to synthesize timedomain waveforms from those spectrograms. Our model achieves a mean opinion score (MOS) of 4.53 comparable to a MOS of 4.58 for professionally recorded speech. To validate our design choices, we present ablation studies of key components of our system and evaluate the impact of using mel spectrograms as the input to WaveNet instead of linguistic, duration, and F_0 features. We further demonstrate that using a compact acoustic intermediate representation enables significant simplification of the WaveNet architecture.

Text-to-speech (TTS) methods have shown promising results in voice cloning, but they require a large number of labeled text-speech pairs. Minimally-supervised speech synthesis decouples TTS by combining two types of discrete speech representations(semantic \& acoustic) and using two sequence-to-sequence tasks to enable training with minimal supervision. However, existing methods suffer from information redundancy and dimension explosion in semantic representation, and high-frequency waveform distortion in discrete acoustic representation. Autoregressive frameworks exhibit typical instability and uncontrollability issues. And non-autoregressive frameworks suffer from prosodic averaging caused by duration prediction models. To address these issues, we propose a minimally-supervised high-fidelity speech synthesis method, where all modules are constructed based on the diffusion models. The non-autoregressive framework enhances controllability, and the duration diffusion model enables diversified prosodic expression. Contrastive Token-Acoustic Pretraining (CTAP) is used as an intermediate semantic representation to solve the problems of information redundancy and dimension explosion in existing semantic coding methods. Mel-spectrogram is used as the acoustic representation. Both semantic and acoustic representations are predicted by continuous variable regression tasks to solve the problem of high-frequency fine-grained waveform distortion. Experimental results show that our proposed method outperforms the baseline method. We provide audio samples on our website.

Limited diversity in standardized benchmarks for evaluating audio representation learning (ARL) methods may hinder systematic comparison of current methods' capabilities. We present ARCH, a comprehensive benchmark for evaluating ARL methods on diverse audio classification domains, covering acoustic events, music, and speech. ARCH comprises 12 datasets, that allow us to thoroughly assess pre-trained SSL models of different sizes. ARCH streamlines benchmarking of ARL techniques through its unified access to a wide range of domains and its ability to readily incorporate new datasets and models. To address the current lack of open-source, pre-trained models for non-speech audio, we also release new pre-trained models that demonstrate strong performance on non-speech datasets. We argue that the presented wide-ranging evaluation provides valuable insights into state-of-the-art ARL methods, and is useful to pinpoint promising research directions.

A key function of auditory cognition is the association of characteristic sounds with their corresponding semantics over time. Humans attempting to discriminate between fine-grained audio categories, often replay the same discriminative sounds to increase their prediction confidence. We propose an end-to-end attention-based architecture that through selective repetition attends over the most discriminative sounds across the audio sequence. Our model initially uses the full audio sequence and iteratively refines the temporal segments replayed based on slot attention. At each playback, the selected segments are replayed using a smaller hop length which represents higher resolution features within these segments. We show that our method can consistently achieve state-of-the-art performance across three audio-classification benchmarks: AudioSet, VGG-Sound, and EPIC-KITCHENS-100.

We present SoundStorm, a model for efficient, non-autoregressive audio generation. SoundStorm receives as input the semantic tokens of AudioLM, and relies on bidirectional attention and confidence-based parallel decoding to generate the tokens of a neural audio codec. Compared to the autoregressive generation approach of AudioLM, our model produces audio of the same quality and with higher consistency in voice and acoustic conditions, while being two orders of magnitude faster. SoundStorm generates 30 seconds of audio in 0.5 seconds on a TPU-v4. We demonstrate the ability of our model to scale audio generation to longer sequences by synthesizing high-quality, natural dialogue segments, given a transcript annotated with speaker turns and a short prompt with the speakers' voices.

This paper presents a speech intelligibility model based on automatic speech recognition (ASR), combining phoneme probabilities from deep neural networks (DNN) and a performance measure that estimates the word error rate from these probabilities. This model does not require the clean speech reference nor the word labels during testing as the ASR decoding step, which finds the most likely sequence of words given phoneme posterior probabilities, is omitted. The model is evaluated via the root-mean-squared error between the predicted and observed speech reception thresholds from eight normal-hearing listeners. The recognition task consists of identifying noisy words from a German matrix sentence test. The speech material was mixed with eight noise maskers covering different modulation types, from speech-shaped stationary noise to a single-talker masker. The prediction performance is compared to five established models and an ASR-model using word labels. Two combinations of features and networks were tested. Both include temporal information either at the feature level (amplitude modulation filterbanks and a feed-forward network) or captured by the architecture (mel-spectrograms and a time-delay deep neural network, TDNN). The TDNN model is on par with the DNN while reducing the number of parameters by a factor of 37; this optimization allows parallel streams on dedicated hearing aid hardware as a forward-pass can be computed within the 10ms of each frame. The proposed model performs almost as well as the label-based model and produces more accurate predictions than the baseline models.

The recent large-scale text-to-speech (TTS) systems are usually grouped as autoregressive and non-autoregressive systems. The autoregressive systems implicitly model duration but exhibit certain deficiencies in robustness and lack of duration controllability. Non-autoregressive systems require explicit alignment information between text and speech during training and predict durations for linguistic units (e.g. phone), which may compromise their naturalness. In this paper, we introduce Masked Generative Codec Transformer (MaskGCT), a fully non-autoregressive TTS model that eliminates the need for explicit alignment information between text and speech supervision, as well as phone-level duration prediction. MaskGCT is a two-stage model: in the first stage, the model uses text to predict semantic tokens extracted from a speech self-supervised learning (SSL) model, and in the second stage, the model predicts acoustic tokens conditioned on these semantic tokens. MaskGCT follows the mask-and-predict learning paradigm. During training, MaskGCT learns to predict masked semantic or acoustic tokens based on given conditions and prompts. During inference, the model generates tokens of a specified length in a parallel manner. Experiments with 100K hours of in-the-wild speech demonstrate that MaskGCT outperforms the current state-of-the-art zero-shot TTS systems in terms of quality, similarity, and intelligibility. Audio samples are available at https://maskgct.github.io/.

Large diffusion models have been successful in text-to-audio (T2A) synthesis tasks, but they often suffer from common issues such as semantic misalignment and poor temporal consistency due to limited natural language understanding and data scarcity. Additionally, 2D spatial structures widely used in T2A works lead to unsatisfactory audio quality when generating variable-length audio samples since they do not adequately prioritize temporal information. To address these challenges, we propose Make-an-Audio 2, a latent diffusion-based T2A method that builds on the success of Make-an-Audio. Our approach includes several techniques to improve semantic alignment and temporal consistency: Firstly, we use pre-trained large language models (LLMs) to parse the text into structured <event & order> pairs for better temporal information capture. We also introduce another structured-text encoder to aid in learning semantic alignment during the diffusion denoising process. To improve the performance of variable length generation and enhance the temporal information extraction, we design a feed-forward Transformer-based diffusion denoiser. Finally, we use LLMs to augment and transform a large amount of audio-label data into audio-text datasets to alleviate the problem of scarcity of temporal data. Extensive experiments show that our method outperforms baseline models in both objective and subjective metrics, and achieves significant gains in temporal information understanding, semantic consistency, and sound quality.

We consider the task of retrieving audio using free-form natural language queries. To study this problem, which has received limited attention in the existing literature, we introduce challenging new benchmarks for text-based audio retrieval using text annotations sourced from the Audiocaps and Clotho datasets. We then employ these benchmarks to establish baselines for cross-modal audio retrieval, where we demonstrate the benefits of pre-training on diverse audio tasks. We hope that our benchmarks will inspire further research into cross-modal text-based audio retrieval with free-form text queries.

Previous real-time MRI (rtMRI)-based speech synthesis models depend heavily on noisy ground-truth speech. Applying loss directly over ground truth mel-spectrograms entangles speech content with MRI noise, resulting in poor intelligibility. We introduce a novel approach that adapts the multi-modal self-supervised AV-HuBERT model for text prediction from rtMRI and incorporates a new flow-based duration predictor for speaker-specific alignment. The predicted text and durations are then used by a speech decoder to synthesize aligned speech in any novel voice. We conduct thorough experiments on two datasets and demonstrate our method's generalization ability to unseen speakers. We assess our framework's performance by masking parts of the rtMRI video to evaluate the impact of different articulators on text prediction. Our method achieves a 15.18% Word Error Rate (WER) on the USC-TIMIT MRI corpus, marking a huge improvement over the current state-of-the-art. Speech samples are available at https://mri2speech.github.io/MRI2Speech/

The goal of the Acoustic Question Answering (AQA) task is to answer a free-form text question about the content of an acoustic scene. It was inspired by the Visual Question Answering (VQA) task. In this paper, based on the previously introduced CLEAR dataset, we propose a new benchmark for AQA, namely CLEAR2, that emphasizes the specific challenges of acoustic inputs. These include handling of variable duration scenes, and scenes built with elementary sounds that differ between training and test set. We also introduce NAAQA, a neural architecture that leverages specific properties of acoustic inputs. The use of 1D convolutions in time and frequency to process 2D spectro-temporal representations of acoustic content shows promising results and enables reductions in model complexity. We show that time coordinate maps augment temporal localization capabilities which enhance performance of the network by ~17 percentage points. On the other hand, frequency coordinate maps have little influence on this task. NAAQA achieves 79.5% of accuracy on the AQA task with ~4 times fewer parameters than the previously explored VQA model. We evaluate the perfomance of NAAQA on an independent data set reconstructed from DAQA. We also test the addition of a MALiMo module in our model on both CLEAR2 and DAQA. We provide a detailed analysis of the results for the different question types. We release the code to produce CLEAR2 as well as NAAQA to foster research in this newly emerging machine learning task.

Learning meaningful and general representations from unannotated speech that are applicable to a wide range of tasks remains challenging. In this paper we propose to use autoregressive predictive coding (APC), a recently proposed self-supervised objective, as a generative pre-training approach for learning meaningful, non-specific, and transferable speech representations. We pre-train APC on large-scale unlabeled data and conduct transfer learning experiments on three speech applications that require different information about speech characteristics to perform well: speech recognition, speech translation, and speaker identification. Extensive experiments show that APC not only outperforms surface features (e.g., log Mel spectrograms) and other popular representation learning methods on all three tasks, but is also effective at reducing downstream labeled data size and model parameters. We also investigate the use of Transformers for modeling APC and find it superior to RNNs.

Recently, there has been an increasing focus on audio-text cross-modal learning. However, most of the existing audio-text datasets contain only simple descriptions of sound events. Compared with classification labels, the advantages of such descriptions are significantly limited. In this paper, we first analyze the detailed information that human descriptions of audio may contain beyond sound event labels. Based on the analysis, we propose an automatic pipeline for curating audio-text pairs with rich details. Leveraging the property that sounds can be mixed and concatenated in the time domain, we control details in four aspects: temporal relationship, loudness, speaker identity, and occurrence number, in simulating audio mixtures. Corresponding details are transformed into captions by large language models. Audio-text pairs with rich details in text descriptions are thereby obtained. We validate the effectiveness of our pipeline with a small amount of simulated data, demonstrating that the simulated data enables models to learn detailed audio captioning.

In this paper we propose a Sequential Representation Quantization AutoEncoder (SeqRQ-AE) to learn from primarily unpaired audio data and produce sequences of representations very close to phoneme sequences of speech utterances. This is achieved by proper temporal segmentation to make the representations phoneme-synchronized, and proper phonetic clustering to have total number of distinct representations close to the number of phonemes. Mapping between the distinct representations and phonemes is learned from a small amount of annotated paired data. Preliminary experiments on LJSpeech demonstrated the learned representations for vowels have relative locations in latent space in good parallel to that shown in the IPA vowel chart defined by linguistics experts. With less than 20 minutes of annotated speech, our method outperformed existing methods on phoneme recognition and is able to synthesize intelligible speech that beats our baseline model.

Sound event localization and detection (SELD) has seen substantial advancements through learning-based methods. These systems, typically trained from scratch on specific datasets, have shown considerable generalization capabilities. Recently, deep neural networks trained on large-scale datasets have achieved remarkable success in the sound event classification (SEC) field, prompting an open question of whether these advancements can be extended to develop general-purpose SELD models. In this paper, leveraging the power of pre-trained SEC models, we propose pre-trained SELD networks (PSELDNets) on large-scale synthetic datasets. These synthetic datasets, generated by convolving sound events with simulated spatial room impulse responses (SRIRs), contain 1,167 hours of audio clips with an ontology of 170 sound classes. These PSELDNets are transferred to downstream SELD tasks. When we adapt PSELDNets to specific scenarios, particularly in low-resource data cases, we introduce a data-efficient fine-tuning method, AdapterBit. PSELDNets are evaluated on a synthetic-test-set using collected SRIRs from TAU Spatial Room Impulse Response Database (TAU-SRIR DB) and achieve satisfactory performance. We also conduct our experiments to validate the transferability of PSELDNets to three publicly available datasets and our own collected audio recordings. Results demonstrate that PSELDNets surpass state-of-the-art systems across all publicly available datasets. Given the need for direction-of-arrival estimation, SELD generally relies on sufficient multi-channel audio clips. However, incorporating the AdapterBit, PSELDNets show more efficient adaptability to various tasks using minimal multi-channel or even just monophonic audio clips, outperforming the traditional fine-tuning approaches.

We propose WHISPER-GPT: A generative large language model (LLM) for speech and music that allows us to work with continuous audio representations and discrete tokens simultaneously as part of a single architecture. There has been a huge surge in generative audio, speech, and music models that utilize discrete audio tokens derived from neural compression algorithms, e.g. ENCODEC. However, one of the major drawbacks of this approach is handling the context length. It blows up for high-fidelity generative architecture if one has to account for all the audio contents at various frequencies for the next token prediction. By combining continuous audio representation like the spectrogram and discrete acoustic tokens, we retain the best of both worlds: Have all the information needed from the audio at a specific time instance in a single token, yet allow LLM to predict the future token to allow for sampling and other benefits discrete space provides. We show how our architecture improves the perplexity and negative log-likelihood scores for the next token prediction compared to a token-based LLM for speech and music.

Foley sound synthesis is crucial for multimedia production, enhancing user experience by synchronizing audio and video both temporally and semantically. Recent studies on automating this labor-intensive process through video-to-sound generation face significant challenges. Systems lacking explicit temporal features suffer from poor controllability and alignment, while timestamp-based models require costly and subjective human annotation. We propose Video-Foley, a video-to-sound system using Root Mean Square (RMS) as a temporal event condition with semantic timbre prompts (audio or text). RMS, a frame-level intensity envelope feature closely related to audio semantics, ensures high controllability and synchronization. The annotation-free self-supervised learning framework consists of two stages, Video2RMS and RMS2Sound, incorporating novel ideas including RMS discretization and RMS-ControlNet with a pretrained text-to-audio model. Our extensive evaluation shows that Video-Foley achieves state-of-the-art performance in audio-visual alignment and controllability for sound timing, intensity, timbre, and nuance. Code, model weights, and demonstrations are available on the accompanying website. (https://jnwnlee.github.io/video-foley-demo)

In this work, we propose novel decoding algorithms to enable streaming automatic speech recognition (ASR) on unsegmented long-form recordings without voice activity detection (VAD), based on monotonic chunkwise attention (MoChA) with an auxiliary connectionist temporal classification (CTC) objective. We propose a block-synchronous beam search decoding to take advantage of efficient batched output-synchronous and low-latency input-synchronous searches. We also propose a VAD-free inference algorithm that leverages CTC probabilities to determine a suitable timing to reset the model states to tackle the vulnerability to long-form data. Experimental evaluations demonstrate that the block-synchronous decoding achieves comparable accuracy to the label-synchronous one. Moreover, the VAD-free inference can recognize long-form speech robustly for up to a few hours.

In this paper, we propose the use of spatial and harmonic features in combination with long short term memory (LSTM) recurrent neural network (RNN) for automatic sound event detection (SED) task. Real life sound recordings typically have many overlapping sound events, making it hard to recognize with just mono channel audio. Human listeners have been successfully recognizing the mixture of overlapping sound events using pitch cues and exploiting the stereo (multichannel) audio signal available at their ears to spatially localize these events. Traditionally SED systems have only been using mono channel audio, motivated by the human listener we propose to extend them to use multichannel audio. The proposed SED system is compared against the state of the art mono channel method on the development subset of TUT sound events detection 2016 database. The usage of spatial and harmonic features are shown to improve the performance of SED.

In this paper, we work on a sound recognition system that continually incorporates new sound classes. Our main goal is to develop a framework where the model can be updated without relying on labeled data. For this purpose, we propose adopting representation learning, where an encoder is trained using unlabeled data. This learning framework enables the study and implementation of a practically relevant use case where only a small amount of the labels is available in a continual learning context. We also make the empirical observation that a similarity-based representation learning method within this framework is robust to forgetting even if no explicit mechanism against forgetting is employed. We show that this approach obtains similar performance compared to several distillation-based continual learning methods when employed on self-supervised representation learning methods.

We consider the generative modeling of speech over multiple minutes, a requirement for long-form multimedia generation and audio-native voice assistants. However, current spoken language models struggle to generate plausible speech past tens of seconds, from high temporal resolution of speech tokens causing loss of coherence, to architectural issues with long-sequence training or extrapolation, to memory costs at inference time. With these considerations we propose SpeechSSM, the first speech language model to learn from and sample long-form spoken audio (e.g., 16 minutes of read or extemporaneous speech) in a single decoding session without text intermediates, based on recent advances in linear-time sequence modeling. Furthermore, to address growing challenges in spoken language evaluation, especially in this new long-form setting, we propose: new embedding-based and LLM-judged metrics; quality measurements over length and time; and a new benchmark for long-form speech processing and generation, LibriSpeech-Long. Speech samples and the dataset are released at https://google.github.io/tacotron/publications/speechssm/

Audio-Language Models (ALMs), which are trained on audio-text data, focus on the processing, understanding, and reasoning of sounds. Unlike traditional supervised learning approaches learning from predefined labels, ALMs utilize natural language as a supervision signal, which is more suitable for describing complex real-world audio recordings. ALMs demonstrate strong zero-shot capabilities and can be flexibly adapted to diverse downstream tasks. These strengths not only enhance the accuracy and generalization of audio processing tasks but also promote the development of models that more closely resemble human auditory perception and comprehension. Recent advances in ALMs have positioned them at the forefront of computer audition research, inspiring a surge of efforts to advance ALM technologies. Despite rapid progress in the field of ALMs, there is still a notable lack of systematic surveys that comprehensively organize and analyze developments. In this paper, we present a comprehensive review of ALMs with a focus on general audio tasks, aiming to fill this gap by providing a structured and holistic overview of ALMs. Specifically, we cover: (1) the background of computer audition and audio-language models; (2) the foundational aspects of ALMs, including prevalent network architectures, training objectives, and evaluation methods; (3) foundational pre-training and audio-language pre-training approaches; (4) task-specific fine-tuning, multi-task tuning and agent systems for downstream applications; (5) datasets and benchmarks; and (6) current challenges and future directions. Our review provides a clear technical roadmap for researchers to understand the development and future trends of existing technologies, offering valuable references for implementation in real-world scenarios.

In this paper, we focus on Whisper, a recent automatic speech recognition model trained with a massive 680k hour labeled speech corpus recorded in diverse conditions. We first show an interesting finding that while Whisper is very robust against real-world background sounds (e.g., music), its audio representation is actually not noise-invariant, but is instead highly correlated to non-speech sounds, indicating that Whisper recognizes speech conditioned on the noise type. With this finding, we build a unified audio tagging and speech recognition model Whisper-AT by freezing the backbone of Whisper, and training a lightweight audio tagging model on top of it. With <1% extra computational cost, Whisper-AT can recognize audio events, in addition to spoken text, in a single forward pass.

The objectives of this work are cross-modal text-audio and audio-text retrieval, in which the goal is to retrieve the audio content from a pool of candidates that best matches a given written description and vice versa. Text-audio retrieval enables users to search large databases through an intuitive interface: they simply issue free-form natural language descriptions of the sound they would like to hear. To study the tasks of text-audio and audio-text retrieval, which have received limited attention in the existing literature, we introduce three challenging new benchmarks. We first construct text-audio and audio-text retrieval benchmarks from the AudioCaps and Clotho audio captioning datasets. Additionally, we introduce the SoundDescs benchmark, which consists of paired audio and natural language descriptions for a diverse collection of sounds that are complementary to those found in AudioCaps and Clotho. We employ these three benchmarks to establish baselines for cross-modal text-audio and audio-text retrieval, where we demonstrate the benefits of pre-training on diverse audio tasks. We hope that our benchmarks will inspire further research into audio retrieval with free-form text queries. Code, audio features for all datasets used, and the SoundDescs dataset are publicly available at https://github.com/akoepke/audio-retrieval-benchmark.

Streaming speech recognition architectures are employed for low-latency, real-time applications. Such architectures are often characterized by their causality. Causal architectures emit tokens at each frame, relying only on current and past signal, while non-causal models are exposed to a window of future frames at each step to increase predictive accuracy. This dichotomy amounts to a trade-off for real-time Automatic Speech Recognition (ASR) system design: profit from the low-latency benefit of strictly-causal architectures while accepting predictive performance limitations, or realize the modeling benefits of future-context models accompanied by their higher latency penalty. In this work, we relax the constraints of this choice and present the Adaptive Non-Causal Attention Transducer (ANCAT). Our architecture is non-causal in the traditional sense, but executes in a low-latency, streaming manner by dynamically choosing when to rely on future context and to what degree within the audio stream. The resulting mechanism, when coupled with our novel regularization algorithms, delivers comparable accuracy to non-causal configurations while improving significantly upon latency, closing the gap with their causal counterparts. We showcase our design experimentally by reporting comparative ASR task results with measures of accuracy and latency on both publicly accessible and production-scale, voice-assistant datasets.

Self-supervised approaches for speech representation learning are challenged by three unique problems: (1) there are multiple sound units in each input utterance, (2) there is no lexicon of input sound units during the pre-training phase, and (3) sound units have variable lengths with no explicit segmentation. To deal with these three problems, we propose the Hidden-Unit BERT (HuBERT) approach for self-supervised speech representation learning, which utilizes an offline clustering step to provide aligned target labels for a BERT-like prediction loss. A key ingredient of our approach is applying the prediction loss over the masked regions only, which forces the model to learn a combined acoustic and language model over the continuous inputs. HuBERT relies primarily on the consistency of the unsupervised clustering step rather than the intrinsic quality of the assigned cluster labels. Starting with a simple k-means teacher of 100 clusters, and using two iterations of clustering, the HuBERT model either matches or improves upon the state-of-the-art wav2vec 2.0 performance on the Librispeech (960h) and Libri-light (60,000h) benchmarks with 10min, 1h, 10h, 100h, and 960h fine-tuning subsets. Using a 1B parameter model, HuBERT shows up to 19% and 13% relative WER reduction on the more challenging dev-other and test-other evaluation subsets.

Stochastic latent variable models (LVMs) achieve state-of-the-art performance on natural image generation but are still inferior to deterministic models on speech. In this paper, we develop a speech benchmark of popular temporal LVMs and compare them against state-of-the-art deterministic models. We report the likelihood, which is a much used metric in the image domain, but rarely, or incomparably, reported for speech models. To assess the quality of the learned representations, we also compare their usefulness for phoneme recognition. Finally, we adapt the Clockwork VAE, a state-of-the-art temporal LVM for video generation, to the speech domain. Despite being autoregressive only in latent space, we find that the Clockwork VAE can outperform previous LVMs and reduce the gap to deterministic models by using a hierarchy of latent variables.

We propose a novel approach for time-scale modification of audio signals. Unlike traditional methods that rely on the framing technique or the short-time Fourier transform to preserve the frequency during temporal stretching, our neural network model encodes the raw audio into a high-level latent representation, dubbed Neuralgram, where each vector represents 1024 audio sample points. Due to a sufficient compression ratio, we are able to apply arbitrary spatial interpolation of the Neuralgram to perform temporal stretching. Finally, a learned neural decoder synthesizes the time-scaled audio samples based on the stretched Neuralgram representation. Both the encoder and decoder are trained with latent regression losses and adversarial losses in order to obtain high-fidelity audio samples. Despite its simplicity, our method has comparable performance compared to the existing baselines and opens a new possibility in research into modern time-scale modification. Audio samples can be found at https://tsmnet-mmasia23.github.io

Scaling text-to-speech to a large and wild dataset has been proven to be highly effective in achieving timbre and speech style generalization, particularly in zero-shot TTS. However, previous works usually encode speech into latent using audio codec and use autoregressive language models or diffusion models to generate it, which ignores the intrinsic nature of speech and may lead to inferior or uncontrollable results. We argue that speech can be decomposed into several attributes (e.g., content, timbre, prosody, and phase) and each of them should be modeled using a module with appropriate inductive biases. From this perspective, we carefully design a novel and large zero-shot TTS system called Mega-TTS, which is trained with large-scale wild data and models different attributes in different ways: 1) Instead of using latent encoded by audio codec as the intermediate feature, we still choose spectrogram as it separates the phase and other attributes very well. Phase can be appropriately constructed by the GAN-based vocoder and does not need to be modeled by the language model. 2) We model the timbre using global vectors since timbre is a global attribute that changes slowly over time. 3) We further use a VQGAN-based acoustic model to generate the spectrogram and a latent code language model to fit the distribution of prosody, since prosody changes quickly over time in a sentence, and language models can capture both local and long-range dependencies. We scale Mega-TTS to multi-domain datasets with 20K hours of speech and evaluate its performance on unseen speakers. Experimental results demonstrate that Mega-TTS surpasses state-of-the-art TTS systems on zero-shot TTS, speech editing, and cross-lingual TTS tasks, with superior naturalness, robustness, and speaker similarity due to the proper inductive bias of each module. Audio samples are available at https://mega-tts.github.io/demo-page.

This report presents the dataset and baseline of Task 3 of the DCASE2021 Challenge on Sound Event Localization and Detection (SELD). The dataset is based on emulation of real recordings of static or moving sound events under real conditions of reverberation and ambient noise, using spatial room impulse responses captured in a variety of rooms and delivered in two spatial formats. The acoustical synthesis remains the same as in the previous iteration of the challenge, however the new dataset brings more challenging conditions of polyphony and overlapping instances of the same class. The most important difference of the new dataset is the introduction of directional interferers, meaning sound events that are localized in space but do not belong to the target classes to be detected and are not annotated. Since such interfering events are expected in every real-world scenario of SELD, the new dataset aims to promote systems that deal with this condition effectively. A modified SELDnet baseline employing the recent ACCDOA representation of SELD problems accompanies the dataset and it is shown to outperform the previous one. The new dataset is shown to be significantly more challenging for both baselines according to all considered metrics. To investigate the individual and combined effects of ambient noise, interferers, and reverberation, we study the performance of the baseline on different versions of the dataset excluding or including combinations of these factors. The results indicate that by far the most detrimental effects are caused by directional interferers.

We present RALL-E, a robust language modeling method for text-to-speech (TTS) synthesis. While previous work based on large language models (LLMs) shows impressive performance on zero-shot TTS, such methods often suffer from poor robustness, such as unstable prosody (weird pitch and rhythm/duration) and a high word error rate (WER), due to the autoregressive prediction style of language models. The core idea behind RALL-E is chain-of-thought (CoT) prompting, which decomposes the task into simpler steps to enhance the robustness of LLM-based TTS. To accomplish this idea, RALL-E first predicts prosody features (pitch and duration) of the input text and uses them as intermediate conditions to predict speech tokens in a CoT style. Second, RALL-E utilizes the predicted duration prompt to guide the computing of self-attention weights in Transformer to enforce the model to focus on the corresponding phonemes and prosody features when predicting speech tokens. Results of comprehensive objective and subjective evaluations demonstrate that, compared to a powerful baseline method VALL-E, RALL-E significantly improves the WER of zero-shot TTS from 6.3% (without reranking) and 2.1% (with reranking) to 2.8% and 1.0%, respectively. Furthermore, we demonstrate that RALL-E correctly synthesizes sentences that are hard for VALL-E and reduces the error rate from 68% to 4%.

We compare self-supervised representation learning algorithms which either explicitly quantize the audio data or learn representations without quantization. We find the former to be more accurate since it builds a good vocabulary of the data through vq-wav2vec [1] to enable learning of effective representations in subsequent BERT training. Different to previous work, we directly fine-tune the pre-trained BERT models on transcribed speech using a Connectionist Temporal Classification (CTC) loss instead of feeding the representations into a task-specific model. We also propose a BERT-style model learning directly from the continuous audio data and compare pre-training on raw audio to spectral features. Fine-tuning a BERT model on 10 hour of labeled Librispeech data with a vq-wav2vec vocabulary is almost as good as the best known reported system trained on 100 hours of labeled data on testclean, while achieving a 25% WER reduction on test-other. When using only 10 minutes of labeled data, WER is 25.2 on test-other and 16.3 on test-clean. This demonstrates that self-supervision can enable speech recognition systems trained on a near-zero amount of transcribed data.

The Transformer architecture has proven to be highly effective for Automatic Speech Recognition (ASR) tasks, becoming a foundational component for a plethora of research in the domain. Historically, many approaches have leaned on fixed-length attention windows, which becomes problematic for varied speech samples in duration and complexity, leading to data over-smoothing and neglect of essential long-term connectivity. Addressing this limitation, we introduce Echo-MSA, a nimble module equipped with a variable-length attention mechanism that accommodates a range of speech sample complexities and durations. This module offers the flexibility to extract speech features across various granularities, spanning from frames and phonemes to words and discourse. The proposed design captures the variable length feature of speech and addresses the limitations of fixed-length attention. Our evaluation leverages a parallel attention architecture complemented by a dynamic gating mechanism that amalgamates traditional attention with the Echo-MSA module output. Empirical evidence from our study reveals that integrating Echo-MSA into the primary model's training regime significantly enhances the word error rate (WER) performance, all while preserving the intrinsic stability of the original model.

We present an approach for recommending a music track for a given video, and vice versa, based on both their temporal alignment and their correspondence at an artistic level. We propose a self-supervised approach that learns this correspondence directly from data, without any need of human annotations. In order to capture the high-level concepts that are required to solve the task, we propose modeling the long-term temporal context of both the video and the music signals, using Transformer networks for each modality. Experiments show that this approach strongly outperforms alternatives that do not exploit the temporal context. The combination of our contributions improve retrieval accuracy up to 10x over prior state of the art. This strong improvement allows us to introduce a wide range of analyses and applications. For instance, we can condition music retrieval based on visually defined attributes.

Neural HMMs are a type of neural transducer recently proposed for sequence-to-sequence modelling in text-to-speech. They combine the best features of classic statistical speech synthesis and modern neural TTS, requiring less data and fewer training updates, and are less prone to gibberish output caused by neural attention failures. In this paper, we combine neural HMM TTS with normalising flows for describing the highly non-Gaussian distribution of speech acoustics. The result is a powerful, fully probabilistic model of durations and acoustics that can be trained using exact maximum likelihood. Compared to dominant flow-based acoustic models, our approach integrates autoregression for improved modelling of long-range dependences such as utterance-level prosody. Experiments show that a system based on our proposal gives more accurate pronunciations and better subjective speech quality than comparable methods, whilst retaining the original advantages of neural HMMs. Audio examples and code are available at https://shivammehta25.github.io/OverFlow/

RNN-T models are widely used in ASR, which rely on the RNN-T loss to achieve length alignment between input audio and target sequence. However, the implementation complexity and the alignment-based optimization target of RNN-T loss lead to computational redundancy and a reduced role for predictor network, respectively. In this paper, we propose a novel model named CIF-Transducer (CIF-T) which incorporates the Continuous Integrate-and-Fire (CIF) mechanism with the RNN-T model to achieve efficient alignment. In this way, the RNN-T loss is abandoned, thus bringing a computational reduction and allowing the predictor network a more significant role. We also introduce Funnel-CIF, Context Blocks, Unified Gating and Bilinear Pooling joint network, and auxiliary training strategy to further improve performance. Experiments on the 178-hour AISHELL-1 and 10000-hour WenetSpeech datasets show that CIF-T achieves state-of-the-art results with lower computational overhead compared to RNN-T models.

Despite the growing interest in unsupervised learning, extracting meaningful knowledge from unlabelled audio remains an open challenge. To take a step in this direction, we recently proposed a problem-agnostic speech encoder (PASE), that combines a convolutional encoder followed by multiple neural networks, called workers, tasked to solve self-supervised problems (i.e., ones that do not require manual annotations as ground truth). PASE was shown to capture relevant speech information, including speaker voice-print and phonemes. This paper proposes PASE+, an improved version of PASE for robust speech recognition in noisy and reverberant environments. To this end, we employ an online speech distortion module, that contaminates the input signals with a variety of random disturbances. We then propose a revised encoder that better learns short- and long-term speech dynamics with an efficient combination of recurrent and convolutional networks. Finally, we refine the set of workers used in self-supervision to encourage better cooperation. Results on TIMIT, DIRHA and CHiME-5 show that PASE+ significantly outperforms both the previous version of PASE as well as common acoustic features. Interestingly, PASE+ learns transferable representations suitable for highly mismatched acoustic conditions.

Our previously proposed MossFormer has achieved promising performance in monaural speech separation. However, it predominantly adopts a self-attention-based MossFormer module, which tends to emphasize longer-range, coarser-scale dependencies, with a deficiency in effectively modelling finer-scale recurrent patterns. In this paper, we introduce a novel hybrid model that provides the capabilities to model both long-range, coarse-scale dependencies and fine-scale recurrent patterns by integrating a recurrent module into the MossFormer framework. Instead of applying the recurrent neural networks (RNNs) that use traditional recurrent connections, we present a recurrent module based on a feedforward sequential memory network (FSMN), which is considered "RNN-free" recurrent network due to the ability to capture recurrent patterns without using recurrent connections. Our recurrent module mainly comprises an enhanced dilated FSMN block by using gated convolutional units (GCU) and dense connections. In addition, a bottleneck layer and an output layer are also added for controlling information flow. The recurrent module relies on linear projections and convolutions for seamless, parallel processing of the entire sequence. The integrated MossFormer2 hybrid model demonstrates remarkable enhancements over MossFormer and surpasses other state-of-the-art methods in WSJ0-2/3mix, Libri2Mix, and WHAM!/WHAMR! benchmarks.

In this paper we present an end-to-end speech recognition model with Transformer encoders that can be used in a streaming speech recognition system. Transformer computation blocks based on self-attention are used to encode both audio and label sequences independently. The activations from both audio and label encoders are combined with a feed-forward layer to compute a probability distribution over the label space for every combination of acoustic frame position and label history. This is similar to the Recurrent Neural Network Transducer (RNN-T) model, which uses RNNs for information encoding instead of Transformer encoders. The model is trained with the RNN-T loss well-suited to streaming decoding. We present results on the LibriSpeech dataset showing that limiting the left context for self-attention in the Transformer layers makes decoding computationally tractable for streaming, with only a slight degradation in accuracy. We also show that the full attention version of our model beats the-state-of-the art accuracy on the LibriSpeech benchmarks. Our results also show that we can bridge the gap between full attention and limited attention versions of our model by attending to a limited number of future frames.

Neural sequence-to-sequence TTS has achieved significantly better output quality than statistical speech synthesis using HMMs. However, neural TTS is generally not probabilistic and uses non-monotonic attention. Attention failures increase training time and can make synthesis babble incoherently. This paper describes how the old and new paradigms can be combined to obtain the advantages of both worlds, by replacing attention in neural TTS with an autoregressive left-right no-skip hidden Markov model defined by a neural network. Based on this proposal, we modify Tacotron 2 to obtain an HMM-based neural TTS model with monotonic alignment, trained to maximise the full sequence likelihood without approximation. We also describe how to combine ideas from classical and contemporary TTS for best results. The resulting example system is smaller and simpler than Tacotron 2, and learns to speak with fewer iterations and less data, whilst achieving comparable naturalness prior to the post-net. Our approach also allows easy control over speaking rate.

We describe a neural network-based system for text-to-speech (TTS) synthesis that is able to generate speech audio in the voice of many different speakers, including those unseen during training. Our system consists of three independently trained components: (1) a speaker encoder network, trained on a speaker verification task using an independent dataset of noisy speech from thousands of speakers without transcripts, to generate a fixed-dimensional embedding vector from seconds of reference speech from a target speaker; (2) a sequence-to-sequence synthesis network based on Tacotron 2, which generates a mel spectrogram from text, conditioned on the speaker embedding; (3) an auto-regressive WaveNet-based vocoder that converts the mel spectrogram into a sequence of time domain waveform samples. We demonstrate that the proposed model is able to transfer the knowledge of speaker variability learned by the discriminatively-trained speaker encoder to the new task, and is able to synthesize natural speech from speakers that were not seen during training. We quantify the importance of training the speaker encoder on a large and diverse speaker set in order to obtain the best generalization performance. Finally, we show that randomly sampled speaker embeddings can be used to synthesize speech in the voice of novel speakers dissimilar from those used in training, indicating that the model has learned a high quality speaker representation.

Open-vocabulary audio-language models, like CLAP, offer a promising approach for zero-shot audio classification (ZSAC) by enabling classification with any arbitrary set of categories specified with natural language prompts. In this paper, we propose a simple but effective method to improve ZSAC with CLAP. Specifically, we shift from the conventional method of using prompts with abstract category labels (e.g., Sound of an organ) to prompts that describe sounds using their inherent descriptive features in a diverse context (e.g.,The organ's deep and resonant tones filled the cathedral.). To achieve this, we first propose ReCLAP, a CLAP model trained with rewritten audio captions for improved understanding of sounds in the wild. These rewritten captions describe each sound event in the original caption using their unique discriminative characteristics. ReCLAP outperforms all baselines on both multi-modal audio-text retrieval and ZSAC. Next, to improve zero-shot audio classification with ReCLAP, we propose prompt augmentation. In contrast to the traditional method of employing hand-written template prompts, we generate custom prompts for each unique label in the dataset. These custom prompts first describe the sound event in the label and then employ them in diverse scenes. Our proposed method improves ReCLAP's performance on ZSAC by 1%-18% and outperforms all baselines by 1% - 55%.

High-quality data labeling from specific domains is costly and human time-consuming. In this work, we propose a self-supervised domain adaptation method, based upon an iterative pseudo-forced alignment algorithm. The produced alignments are employed to customize an end-to-end Automatic Speech Recognition (ASR) and iteratively refined. The algorithm is fed with frame-wise character posteriors produced by a seed ASR, trained with out-of-domain data, and optimized throughout a Connectionist Temporal Classification (CTC) loss. The alignments are computed iteratively upon a corpus of broadcast TV. The process is repeated by reducing the quantity of text to be aligned or expanding the alignment window until finding the best possible audio-text alignment. The starting timestamps, or temporal anchors, are produced uniquely based on the confidence score of the last aligned utterance. This score is computed with the paths of the CTC-alignment matrix. With this methodology, no human-revised text references are required. Alignments from long audio files with low-quality transcriptions, like TV captions, are filtered out by confidence score and ready for further ASR adaptation. The obtained results, on both the Spanish RTVE2022 and CommonVoice databases, underpin the feasibility of using CTC-based systems to perform: highly accurate audio-text alignments, domain adaptation and semi-supervised training of end-to-end ASR.

This paper describes the Microsoft end-to-end neural text to speech (TTS) system: DelightfulTTS for Blizzard Challenge 2021. The goal of this challenge is to synthesize natural and high-quality speech from text, and we approach this goal in two perspectives: The first is to directly model and generate waveform in 48 kHz sampling rate, which brings higher perception quality than previous systems with 16 kHz or 24 kHz sampling rate; The second is to model the variation information in speech through a systematic design, which improves the prosody and naturalness. Specifically, for 48 kHz modeling, we predict 16 kHz mel-spectrogram in acoustic model, and propose a vocoder called HiFiNet to directly generate 48 kHz waveform from predicted 16 kHz mel-spectrogram, which can better trade off training efficiency, modelling stability and voice quality. We model variation information systematically from both explicit (speaker ID, language ID, pitch and duration) and implicit (utterance-level and phoneme-level prosody) perspectives: 1) For speaker and language ID, we use lookup embedding in training and inference; 2) For pitch and duration, we extract the values from paired text-speech data in training and use two predictors to predict the values in inference; 3) For utterance-level and phoneme-level prosody, we use two reference encoders to extract the values in training, and use two separate predictors to predict the values in inference. Additionally, we introduce an improved Conformer block to better model the local and global dependency in acoustic model. For task SH1, DelightfulTTS achieves 4.17 mean score in MOS test and 4.35 in SMOS test, which indicates the effectiveness of our proposed system

Speech-to-text alignment is a critical component of neural textto-speech (TTS) models. Autoregressive TTS models typically use an attention mechanism to learn these alignments on-line. However, these alignments tend to be brittle and often fail to generalize to long utterances and out-of-domain text, leading to missing or repeating words. Most non-autoregressive endto-end TTS models rely on durations extracted from external sources. In this paper we leverage the alignment mechanism proposed in RAD-TTS as a generic alignment learning framework, easily applicable to a variety of neural TTS models. The framework combines forward-sum algorithm, the Viterbi algorithm, and a simple and efficient static prior. In our experiments, the alignment learning framework improves all tested TTS architectures, both autoregressive (Flowtron, Tacotron 2) and non-autoregressive (FastPitch, FastSpeech 2, RAD-TTS). Specifically, it improves alignment convergence speed of existing attention-based mechanisms, simplifies the training pipeline, and makes the models more robust to errors on long utterances. Most importantly, the framework improves the perceived speech synthesis quality, as judged by human evaluators.

Most existing datasets for sound event recognition (SER) are relatively small and/or domain-specific, with the exception of AudioSet, based on over 2M tracks from YouTube videos and encompassing over 500 sound classes. However, AudioSet is not an open dataset as its official release consists of pre-computed audio features. Downloading the original audio tracks can be problematic due to YouTube videos gradually disappearing and usage rights issues. To provide an alternative benchmark dataset and thus foster SER research, we introduce FSD50K, an open dataset containing over 51k audio clips totalling over 100h of audio manually labeled using 200 classes drawn from the AudioSet Ontology. The audio clips are licensed under Creative Commons licenses, making the dataset freely distributable (including waveforms). We provide a detailed description of the FSD50K creation process, tailored to the particularities of Freesound data, including challenges encountered and solutions adopted. We include a comprehensive dataset characterization along with discussion of limitations and key factors to allow its audio-informed usage. Finally, we conduct sound event classification experiments to provide baseline systems as well as insight on the main factors to consider when splitting Freesound audio data for SER. Our goal is to develop a dataset to be widely adopted by the community as a new open benchmark for SER research.

We propose vq-wav2vec to learn discrete representations of audio segments through a wav2vec-style self-supervised context prediction task. The algorithm uses either a gumbel softmax or online k-means clustering to quantize the dense representations. Discretization enables the direct application of algorithms from the NLP community which require discrete inputs. Experiments show that BERT pre-training achieves a new state of the art on TIMIT phoneme classification and WSJ speech recognition.

Neural network based end-to-end text to speech (TTS) has significantly improved the quality of synthesized speech. Prominent methods (e.g., Tacotron 2) usually first generate mel-spectrogram from text, and then synthesize speech from the mel-spectrogram using vocoder such as WaveNet. Compared with traditional concatenative and statistical parametric approaches, neural network based end-to-end models suffer from slow inference speed, and the synthesized speech is usually not robust (i.e., some words are skipped or repeated) and lack of controllability (voice speed or prosody control). In this work, we propose a novel feed-forward network based on Transformer to generate mel-spectrogram in parallel for TTS. Specifically, we extract attention alignments from an encoder-decoder based teacher model for phoneme duration prediction, which is used by a length regulator to expand the source phoneme sequence to match the length of the target mel-spectrogram sequence for parallel mel-spectrogram generation. Experiments on the LJSpeech dataset show that our parallel model matches autoregressive models in terms of speech quality, nearly eliminates the problem of word skipping and repeating in particularly hard cases, and can adjust voice speed smoothly. Most importantly, compared with autoregressive Transformer TTS, our model speeds up mel-spectrogram generation by 270x and the end-to-end speech synthesis by 38x. Therefore, we call our model FastSpeech.

In recent years, much speech separation research has focused primarily on improving model performance. However, for low-latency speech processing systems, high efficiency is equally important. Therefore, we propose a speech separation model with significantly reduced parameters and computational costs: Time-frequency Interleaved Gain Extraction and Reconstruction network (TIGER). TIGER leverages prior knowledge to divide frequency bands and compresses frequency information. We employ a multi-scale selective attention module to extract contextual features, while introducing a full-frequency-frame attention module to capture both temporal and frequency contextual information. Additionally, to more realistically evaluate the performance of speech separation models in complex acoustic environments, we introduce a dataset called EchoSet. This dataset includes noise and more realistic reverberation (e.g., considering object occlusions and material properties), with speech from two speakers overlapping at random proportions. Experimental results showed that models trained on EchoSet had better generalization ability than those trained on other datasets to the data collected in the physical world, which validated the practical value of the EchoSet. On EchoSet and real-world data, TIGER significantly reduces the number of parameters by 94.3% and the MACs by 95.3% while achieving performance surpassing state-of-the-art (SOTA) model TF-GridNet. This is the first speech separation model with fewer than 1 million parameters that achieves performance comparable to the SOTA model.

We show for the first time that learning powerful representations from speech audio alone followed by fine-tuning on transcribed speech can outperform the best semi-supervised methods while being conceptually simpler. wav2vec 2.0 masks the speech input in the latent space and solves a contrastive task defined over a quantization of the latent representations which are jointly learned. Experiments using all labeled data of Librispeech achieve 1.8/3.3 WER on the clean/other test sets. When lowering the amount of labeled data to one hour, wav2vec 2.0 outperforms the previous state of the art on the 100 hour subset while using 100 times less labeled data. Using just ten minutes of labeled data and pre-training on 53k hours of unlabeled data still achieves 4.8/8.2 WER. This demonstrates the feasibility of speech recognition with limited amounts of labeled data.

Recent years have seen progress beyond domain-specific sound separation for speech or music towards universal sound separation for arbitrary sounds. Prior work on universal sound separation has investigated separating a target sound out of an audio mixture given a text query. Such text-queried sound separation systems provide a natural and scalable interface for specifying arbitrary target sounds. However, supervised text-queried sound separation systems require costly labeled audio-text pairs for training. Moreover, the audio provided in existing datasets is often recorded in a controlled environment, causing a considerable generalization gap to noisy audio in the wild. In this work, we aim to approach text-queried universal sound separation by using only unlabeled data. We propose to leverage the visual modality as a bridge to learn the desired audio-textual correspondence. The proposed CLIPSep model first encodes the input query into a query vector using the contrastive language-image pretraining (CLIP) model, and the query vector is then used to condition an audio separation model to separate out the target sound. While the model is trained on image-audio pairs extracted from unlabeled videos, at test time we can instead query the model with text inputs in a zero-shot setting, thanks to the joint language-image embedding learned by the CLIP model. Further, videos in the wild often contain off-screen sounds and background noise that may hinder the model from learning the desired audio-textual correspondence. To address this problem, we further propose an approach called noise invariant training for training a query-based sound separation model on noisy data. Experimental results show that the proposed models successfully learn text-queried universal sound separation using only noisy unlabeled videos, even achieving competitive performance against a supervised model in some settings.

Most music source separation systems require large collections of isolated sources for training, which can be difficult to obtain. In this work, we use musical scores, which are comparatively easy to obtain, as a weak label for training a source separation system. In contrast with previous score-informed separation approaches, our system does not require isolated sources, and score is used only as a training target, not required for inference. Our model consists of a separator that outputs a time-frequency mask for each instrument, and a transcriptor that acts as a critic, providing both temporal and frequency supervision to guide the learning of the separator. A harmonic mask constraint is introduced as another way of leveraging score information during training, and we propose two novel adversarial losses for additional fine-tuning of both the transcriptor and the separator. Results demonstrate that using score information outperforms temporal weak-labels, and adversarial structures lead to further improvements in both separation and transcription performance.

This paper introduces WaveNet, a deep neural network for generating raw audio waveforms. The model is fully probabilistic and autoregressive, with the predictive distribution for each audio sample conditioned on all previous ones; nonetheless we show that it can be efficiently trained on data with tens of thousands of samples per second of audio. When applied to text-to-speech, it yields state-of-the-art performance, with human listeners rating it as significantly more natural sounding than the best parametric and concatenative systems for both English and Mandarin. A single WaveNet can capture the characteristics of many different speakers with equal fidelity, and can switch between them by conditioning on the speaker identity. When trained to model music, we find that it generates novel and often highly realistic musical fragments. We also show that it can be employed as a discriminative model, returning promising results for phoneme recognition.

We introduce Moshi, a speech-text foundation model and full-duplex spoken dialogue framework. Current systems for spoken dialogue rely on pipelines of independent components, namely voice activity detection, speech recognition, textual dialogue and text-to-speech. Such frameworks cannot emulate the experience of real conversations. First, their complexity induces a latency of several seconds between interactions. Second, text being the intermediate modality for dialogue, non-linguistic information that modifies meaning -- such as emotion or non-speech sounds -- is lost in the interaction. Finally, they rely on a segmentation into speaker turns, which does not take into account overlapping speech, interruptions and interjections. Moshi solves these independent issues altogether by casting spoken dialogue as speech-to-speech generation. Starting from a text language model backbone, Moshi generates speech as tokens from the residual quantizer of a neural audio codec, while modeling separately its own speech and that of the user into parallel streams. This allows for the removal of explicit speaker turns, and the modeling of arbitrary conversational dynamics. We moreover extend the hierarchical semantic-to-acoustic token generation of previous work to first predict time-aligned text tokens as a prefix to audio tokens. Not only this "Inner Monologue" method significantly improves the linguistic quality of generated speech, but we also illustrate how it can provide streaming speech recognition and text-to-speech. Our resulting model is the first real-time full-duplex spoken large language model, with a theoretical latency of 160ms, 200ms in practice, and is available at https://github.com/kyutai-labs/moshi.

We propose a novel text-to-speech (TTS) framework centered around a neural transducer. Our approach divides the whole TTS pipeline into semantic-level sequence-to-sequence (seq2seq) modeling and fine-grained acoustic modeling stages, utilizing discrete semantic tokens obtained from wav2vec2.0 embeddings. For a robust and efficient alignment modeling, we employ a neural transducer named token transducer for the semantic token prediction, benefiting from its hard monotonic alignment constraints. Subsequently, a non-autoregressive (NAR) speech generator efficiently synthesizes waveforms from these semantic tokens. Additionally, a reference speech controls temporal dynamics and acoustic conditions at each stage. This decoupled framework reduces the training complexity of TTS while allowing each stage to focus on semantic and acoustic modeling. Our experimental results on zero-shot adaptive TTS demonstrate that our model surpasses the baseline in terms of speech quality and speaker similarity, both objectively and subjectively. We also delve into the inference speed and prosody control capabilities of our approach, highlighting the potential of neural transducers in TTS frameworks.

Speech language models have recently demonstrated great potential as universal speech processing systems. Such models have the ability to model the rich acoustic information existing in audio signals, beyond spoken content, such as emotion, background noise, etc. Despite this, evaluation benchmarks which evaluate awareness to a wide range of acoustic aspects, are lacking. To help bridge this gap, we introduce SALMon, a novel evaluation suite encompassing background noise, emotion, speaker identity and room impulse response. The proposed benchmarks both evaluate the consistency of the inspected element and how much it matches the spoken text. We follow a modelling based approach, measuring whether a model gives correct samples higher scores than incorrect ones. This approach makes the benchmark fast to compute even for large models. We evaluated several speech language models on SALMon, thus highlighting the strengths and weaknesses of each evaluated method. Code and data are publicly available at https://pages.cs.huji.ac.il/adiyoss-lab/salmon/ .

Inspired by the recent progress in self-supervised learning for computer vision that generates supervision using data augmentations, we explore a new general-purpose audio representation learning approach. We propose learning general-purpose audio representation from a single audio segment without expecting relationships between different time segments of audio samples. To implement this principle, we introduce Bootstrap Your Own Latent (BYOL) for Audio (BYOL-A, pronounced "viola"), an audio self-supervised learning method based on BYOL for learning general-purpose audio representation. Unlike most previous audio self-supervised learning methods that rely on agreement of vicinity audio segments or disagreement of remote ones, BYOL-A creates contrasts in an augmented audio segment pair derived from a single audio segment. With a combination of normalization and augmentation techniques, BYOL-A achieves state-of-the-art results in various downstream tasks. Extensive ablation studies also clarified the contribution of each component and their combinations.

Self-supervised speech representation learning has become essential for extracting meaningful features from untranscribed audio. Recent advances highlight the potential of deriving discrete symbols from the features correlated with linguistic units, which enables text-less training across diverse tasks. In particular, sentence-level Self-Distillation of the pretrained HuBERT (SD-HuBERT) induces syllabic structures within latent speech frame representations extracted from an intermediate Transformer layer. In SD-HuBERT, sentence-level representation is accumulated from speech frame features through self-attention layers using a special CLS token. However, we observe that the information aggregated in the CLS token correlates more with speaker identity than with linguistic content. To address this, we propose a speech-only self-supervised fine-tuning approach that separates syllabic units from speaker information. Our method introduces speaker perturbation as data augmentation and adopts a frame-level training objective to prevent the CLS token from aggregating paralinguistic information. Experimental results show that our approach surpasses the current state-of-the-art method in most syllable segmentation and syllabic unit quality metrics on Librispeech, underscoring its effectiveness in promoting syllabic organization within speech-only models.

Learning to classify time series with limited data is a practical yet challenging problem. Current methods are primarily based on hand-designed feature extraction rules or domain-specific data augmentation. Motivated by the advances in deep speech processing models and the fact that voice data are univariate temporal signals, in this paper, we propose Voice2Series (V2S), a novel end-to-end approach that reprograms acoustic models for time series classification, through input transformation learning and output label mapping. Leveraging the representation learning power of a large-scale pre-trained speech processing model, on 30 different time series tasks we show that V2S performs competitive results on 19 time series classification tasks. We further provide a theoretical justification of V2S by proving its population risk is upper bounded by the source risk and a Wasserstein distance accounting for feature alignment via reprogramming. Our results offer new and effective means to time series classification.

Audio-Language models jointly learn multimodal text and audio representations that enable Zero-Shot inference. Models rely on the encoders to create powerful representations of the input and generalize to multiple tasks ranging from sounds, music, and speech. Although models have achieved remarkable performance, there is still a performance gap with task-specific models. In this paper, we propose a Contrastive Language-Audio Pretraining model that is pretrained with a diverse collection of 4.6M audio-text pairs employing two innovative encoders for Zero-Shot inference. To learn audio representations, we trained an audio encoder on 22 audio tasks, instead of the standard training of sound event classification. To learn language representations, we trained an autoregressive decoder-only model instead of the standard encoder-only models. Then, the audio and language representations are brought into a joint multimodal space using Contrastive Learning. We used our encoders to improve the downstream performance by a margin. We extensively evaluated the generalization of our representations on 26 downstream tasks, the largest in the literature. Our model achieves state of the art results in several tasks leading the way towards general-purpose audio representations.

In this work, we investigate two popular end-to-end automatic speech recognition (ASR) models, namely Connectionist Temporal Classification (CTC) and RNN-Transducer (RNN-T), for offline recognition of voice search queries, with up to 2B model parameters. The encoders of our models use the neural architecture of Google's universal speech model (USM), with additional funnel pooling layers to significantly reduce the frame rate and speed up training and inference. We perform extensive studies on vocabulary size, time reduction strategy, and its generalization performance on long-form test sets. Despite the speculation that, as the model size increases, CTC can be as good as RNN-T which builds label dependency into the prediction, we observe that a 900M RNN-T clearly outperforms a 1.8B CTC and is more tolerant to severe time reduction, although the WER gap can be largely removed by LM shallow fusion.

This survey paper provides a comprehensive overview of the recent advancements and challenges in applying large language models to the field of audio signal processing. Audio processing, with its diverse signal representations and a wide range of sources--from human voices to musical instruments and environmental sounds--poses challenges distinct from those found in traditional Natural Language Processing scenarios. Nevertheless, Large Audio Models, epitomized by transformer-based architectures, have shown marked efficacy in this sphere. By leveraging massive amount of data, these models have demonstrated prowess in a variety of audio tasks, spanning from Automatic Speech Recognition and Text-To-Speech to Music Generation, among others. Notably, recently these Foundational Audio Models, like SeamlessM4T, have started showing abilities to act as universal translators, supporting multiple speech tasks for up to 100 languages without any reliance on separate task-specific systems. This paper presents an in-depth analysis of state-of-the-art methodologies regarding Foundational Large Audio Models, their performance benchmarks, and their applicability to real-world scenarios. We also highlight current limitations and provide insights into potential future research directions in the realm of Large Audio Models with the intent to spark further discussion, thereby fostering innovation in the next generation of audio-processing systems. Furthermore, to cope with the rapid development in this area, we will consistently update the relevant repository with relevant recent articles and their open-source implementations at https://github.com/EmulationAI/awesome-large-audio-models.

Semantic information refers to the meaning conveyed through words, phrases, and contextual relationships within a given linguistic structure. Humans can leverage semantic information, such as familiar linguistic patterns and contextual cues, to reconstruct incomplete or masked speech signals in noisy environments. However, existing speech enhancement (SE) approaches often overlook the rich semantic information embedded in speech, which is crucial for improving intelligibility, speaker consistency, and overall quality of enhanced speech signals. To enrich the SE model with semantic information, we employ language models as an efficient semantic learner and propose a comprehensive framework tailored for language model-based speech enhancement, called GenSE. Specifically, we approach SE as a conditional language modeling task rather than a continuous signal regression problem defined in existing works. This is achieved by tokenizing speech signals into semantic tokens using a pre-trained self-supervised model and into acoustic tokens using a custom-designed single-quantizer neural codec model. To improve the stability of language model predictions, we propose a hierarchical modeling method that decouples the generation of clean semantic tokens and clean acoustic tokens into two distinct stages. Moreover, we introduce a token chain prompting mechanism during the acoustic token generation stage to ensure timbre consistency throughout the speech enhancement process. Experimental results on benchmark datasets demonstrate that our proposed approach outperforms state-of-the-art SE systems in terms of speech quality and generalization capability.

Current leading Text-To-Audio (TTA) generation models suffer from degraded performance on zero-shot and few-shot settings. It is often challenging to generate high-quality audio for audio events that are unseen or uncommon in the training set. Inspired by the success of Retrieval-Augmented Generation (RAG) in Large Language Model (LLM)-based knowledge-intensive tasks, we extend the TTA process with additional conditioning contexts. We propose Audiobox TTA-RAG, a novel retrieval-augmented TTA approach based on Audiobox, a conditional flow-matching audio generation model. Unlike the vanilla Audiobox TTA solution which generates audio conditioned on text, we augmented the conditioning input with retrieved audio samples that provide additional acoustic information to generate the target audio. Our retrieval method does not require the external database to have labeled audio, offering more practical use cases. To evaluate our proposed method, we curated test sets in zero-shot and few-shot settings. Our empirical results show that the proposed model can effectively leverage the retrieved audio samples and significantly improve zero-shot and few-shot TTA performance, with large margins on multiple evaluation metrics, while maintaining the ability to generate semantically aligned audio for the in-domain setting. In addition, we investigate the effect of different retrieval methods and data sources.

Token-based text-to-speech (TTS) models have emerged as a promising avenue for generating natural and realistic speech, yet they grapple with low pronunciation accuracy, speaking style and timbre inconsistency, and a substantial need for diverse training data. In response, we introduce a novel hierarchical acoustic modeling approach complemented by a tailored data augmentation strategy and train it on the combination of real and synthetic data, scaling the data size up to 650k hours, leading to the zero-shot TTS model with 0.8B parameters. Specifically, our method incorporates a latent variable sequence containing supplementary acoustic information based on refined self-supervised learning (SSL) discrete units into the TTS model by a predictor. This significantly mitigates pronunciation errors and style mutations in synthesized speech. During training, we strategically replace and duplicate segments of the data to enhance timbre uniformity. Moreover, a pretrained few-shot voice conversion model is utilized to generate a plethora of voices with identical content yet varied timbres. This facilitates the explicit learning of utterance-level one-to-many mappings, enriching speech diversity and also ensuring consistency in timbre. Comparative experiments (Demo page: https://anonymous.4open.science/w/ham-tts/)demonstrate our model's superiority over VALL-E in pronunciation precision and maintaining speaking style, as well as timbre continuity.

We tackle the problem of generating audio samples conditioned on descriptive text captions. In this work, we propose AaudioGen, an auto-regressive generative model that generates audio samples conditioned on text inputs. AudioGen operates on a learnt discrete audio representation. The task of text-to-audio generation poses multiple challenges. Due to the way audio travels through a medium, differentiating ``objects'' can be a difficult task (e.g., separating multiple people simultaneously speaking). This is further complicated by real-world recording conditions (e.g., background noise, reverberation, etc.). Scarce text annotations impose another constraint, limiting the ability to scale models. Finally, modeling high-fidelity audio requires encoding audio at high sampling rate, leading to extremely long sequences. To alleviate the aforementioned challenges we propose an augmentation technique that mixes different audio samples, driving the model to internally learn to separate multiple sources. We curated 10 datasets containing different types of audio and text annotations to handle the scarcity of text-audio data points. For faster inference, we explore the use of multi-stream modeling, allowing the use of shorter sequences while maintaining a similar bitrate and perceptual quality. We apply classifier-free guidance to improve adherence to text. Comparing to the evaluated baselines, AudioGen outperforms over both objective and subjective metrics. Finally, we explore the ability of the proposed method to generate audio continuation conditionally and unconditionally. Samples: https://felixkreuk.github.io/audiogen

We present a joint audio-visual model for isolating a single speech signal from a mixture of sounds such as other speakers and background noise. Solving this task using only audio as input is extremely challenging and does not provide an association of the separated speech signals with speakers in the video. In this paper, we present a deep network-based model that incorporates both visual and auditory signals to solve this task. The visual features are used to "focus" the audio on desired speakers in a scene and to improve the speech separation quality. To train our joint audio-visual model, we introduce AVSpeech, a new dataset comprised of thousands of hours of video segments from the Web. We demonstrate the applicability of our method to classic speech separation tasks, as well as real-world scenarios involving heated interviews, noisy bars, and screaming children, only requiring the user to specify the face of the person in the video whose speech they want to isolate. Our method shows clear advantage over state-of-the-art audio-only speech separation in cases of mixed speech. In addition, our model, which is speaker-independent (trained once, applicable to any speaker), produces better results than recent audio-visual speech separation methods that are speaker-dependent (require training a separate model for each speaker of interest).

Despite recent progress in text-to-audio (TTA) generation, we show that the state-of-the-art models, such as AudioLDM, trained on datasets with an imbalanced class distribution, such as AudioCaps, are biased in their generation performance. Specifically, they excel in generating common audio classes while underperforming in the rare ones, thus degrading the overall generation performance. We refer to this problem as long-tailed text-to-audio generation. To address this issue, we propose a simple retrieval-augmented approach for TTA models. Specifically, given an input text prompt, we first leverage a Contrastive Language Audio Pretraining (CLAP) model to retrieve relevant text-audio pairs. The features of the retrieved audio-text data are then used as additional conditions to guide the learning of TTA models. We enhance AudioLDM with our proposed approach and denote the resulting augmented system as Re-AudioLDM. On the AudioCaps dataset, Re-AudioLDM achieves a state-of-the-art Frechet Audio Distance (FAD) of 1.37, outperforming the existing approaches by a large margin. Furthermore, we show that Re-AudioLDM can generate realistic audio for complex scenes, rare audio classes, and even unseen audio types, indicating its potential in TTA tasks.

Non-autoregressive text to speech (TTS) models such as FastSpeech can synthesize speech significantly faster than previous autoregressive models with comparable quality. The training of FastSpeech model relies on an autoregressive teacher model for duration prediction (to provide more information as input) and knowledge distillation (to simplify the data distribution in output), which can ease the one-to-many mapping problem (i.e., multiple speech variations correspond to the same text) in TTS. However, FastSpeech has several disadvantages: 1) the teacher-student distillation pipeline is complicated and time-consuming, 2) the duration extracted from the teacher model is not accurate enough, and the target mel-spectrograms distilled from teacher model suffer from information loss due to data simplification, both of which limit the voice quality. In this paper, we propose FastSpeech 2, which addresses the issues in FastSpeech and better solves the one-to-many mapping problem in TTS by 1) directly training the model with ground-truth target instead of the simplified output from teacher, and 2) introducing more variation information of speech (e.g., pitch, energy and more accurate duration) as conditional inputs. Specifically, we extract duration, pitch and energy from speech waveform and directly take them as conditional inputs in training and use predicted values in inference. We further design FastSpeech 2s, which is the first attempt to directly generate speech waveform from text in parallel, enjoying the benefit of fully end-to-end inference. Experimental results show that 1) FastSpeech 2 achieves a 3x training speed-up over FastSpeech, and FastSpeech 2s enjoys even faster inference speed; 2) FastSpeech 2 and 2s outperform FastSpeech in voice quality, and FastSpeech 2 can even surpass autoregressive models. Audio samples are available at https://speechresearch.github.io/fastspeech2/.

Speech emotion recognition (SER) plays a vital role in improving the interactions between humans and machines by inferring human emotion and affective states from speech signals. Whereas recent works primarily focus on mining spatiotemporal information from hand-crafted features, we explore how to model the temporal patterns of speech emotions from dynamic temporal scales. Towards that goal, we introduce a novel temporal emotional modeling approach for SER, termed Temporal-aware bI-direction Multi-scale Network (TIM-Net), which learns multi-scale contextual affective representations from various time scales. Specifically, TIM-Net first employs temporal-aware blocks to learn temporal affective representation, then integrates complementary information from the past and the future to enrich contextual representations, and finally, fuses multiple time scale features for better adaptation to the emotional variation. Extensive experimental results on six benchmark SER datasets demonstrate the superior performance of TIM-Net, gaining 2.34% and 2.61% improvements of the average UAR and WAR over the second-best on each corpus. The source code is available at https://github.com/Jiaxin-Ye/TIM-Net_SER.

Despite significant advancements in neural text-to-audio generation, challenges persist in controllability and evaluation. This paper addresses these issues through the Sound Scene Synthesis challenge held as part of the Detection and Classification of Acoustic Scenes and Events 2024. We present an evaluation protocol combining objective metric, namely Fr\'echet Audio Distance, with perceptual assessments, utilizing a structured prompt format to enable diverse captions and effective evaluation. Our analysis reveals varying performance across sound categories and model architectures, with larger models generally excelling but innovative lightweight approaches also showing promise. The strong correlation between objective metrics and human ratings validates our evaluation approach. We discuss outcomes in terms of audio quality, controllability, and architectural considerations for text-to-audio synthesizers, providing direction for future research.

Recently, speech-text pre-training methods have shown remarkable success in many speech and natural language processing tasks. However, most previous pre-trained models are usually tailored for one or two specific tasks, but fail to conquer a wide range of speech-text tasks. In addition, existing speech-text pre-training methods fail to explore the contextual information within a dialogue to enrich utterance representations. In this paper, we propose Speech-text dialog Pre-training for spoken dialog understanding with ExpliCiT cRoss-Modal Alignment (SPECTRA), which is the first-ever speech-text dialog pre-training model. Concretely, to consider the temporality of speech modality, we design a novel temporal position prediction task to capture the speech-text alignment. This pre-training task aims to predict the start and end time of each textual word in the corresponding speech waveform. In addition, to learn the characteristics of spoken dialogs, we generalize a response selection task from textual dialog pre-training to speech-text dialog pre-training scenarios. Experimental results on four different downstream speech-text tasks demonstrate the superiority of SPECTRA in learning speech-text alignment and multi-turn dialog context.

In this paper, we introduce SoloAudio, a novel diffusion-based generative model for target sound extraction (TSE). Our approach trains latent diffusion models on audio, replacing the previous U-Net backbone with a skip-connected Transformer that operates on latent features. SoloAudio supports both audio-oriented and language-oriented TSE by utilizing a CLAP model as the feature extractor for target sounds. Furthermore, SoloAudio leverages synthetic audio generated by state-of-the-art text-to-audio models for training, demonstrating strong generalization to out-of-domain data and unseen sound events. We evaluate this approach on the FSD Kaggle 2018 mixture dataset and real data from AudioSet, where SoloAudio achieves the state-of-the-art results on both in-domain and out-of-domain data, and exhibits impressive zero-shot and few-shot capabilities. Source code and demos are released.

Recently proposed self-supervised learning approaches have been successful for pre-training speech representation models. The utility of these learned representations has been observed empirically, but not much has been studied about the type or extent of information encoded in the pre-trained representations themselves. Developing such insights can help understand the capabilities and limits of these models and enable the research community to more efficiently develop their usage for downstream applications. In this work, we begin to fill this gap by examining one recent and successful pre-trained model (wav2vec 2.0), via its intermediate representation vectors, using a suite of analysis tools. We use the metrics of canonical correlation, mutual information, and performance on simple downstream tasks with non-parametric probes, in order to (i) query for acoustic and linguistic information content, (ii) characterize the evolution of information across model layers, and (iii) understand how fine-tuning the model for automatic speech recognition (ASR) affects these observations. Our findings motivate modifying the fine-tuning protocol for ASR, which produces improved word error rates in a low-resource setting.

Spiking Neural Networks (SNNs) are a promising research direction for building power-efficient information processing systems, especially for temporal tasks such as speech recognition. In SNNs, delays refer to the time needed for one spike to travel from one neuron to another. These delays matter because they influence the spike arrival times, and it is well-known that spiking neurons respond more strongly to coincident input spikes. More formally, it has been shown theoretically that plastic delays greatly increase the expressivity in SNNs. Yet, efficient algorithms to learn these delays have been lacking. Here, we propose a new discrete-time algorithm that addresses this issue in deep feedforward SNNs using backpropagation, in an offline manner. To simulate delays between consecutive layers, we use 1D convolutions across time. The kernels contain only a few non-zero weights - one per synapse - whose positions correspond to the delays. These positions are learned together with the weights using the recently proposed Dilated Convolution with Learnable Spacings (DCLS). We evaluated our method on three datasets: the Spiking Heidelberg Dataset (SHD), the Spiking Speech Commands (SSC) and its non-spiking version Google Speech Commands v0.02 (GSC) benchmarks, which require detecting temporal patterns. We used feedforward SNNs with two or three hidden fully connected layers, and vanilla leaky integrate-and-fire neurons. We showed that fixed random delays help and that learning them helps even more. Furthermore, our method outperformed the state-of-the-art in the three datasets without using recurrent connections and with substantially fewer parameters. Our work demonstrates the potential of delay learning in developing accurate and precise models for temporal data processing. Our code is based on PyTorch / SpikingJelly and available at: https://github.com/Thvnvtos/SNN-delays

We introduce AudioLM, a framework for high-quality audio generation with long-term consistency. AudioLM maps the input audio to a sequence of discrete tokens and casts audio generation as a language modeling task in this representation space. We show how existing audio tokenizers provide different trade-offs between reconstruction quality and long-term structure, and we propose a hybrid tokenization scheme to achieve both objectives. Namely, we leverage the discretized activations of a masked language model pre-trained on audio to capture long-term structure and the discrete codes produced by a neural audio codec to achieve high-quality synthesis. By training on large corpora of raw audio waveforms, AudioLM learns to generate natural and coherent continuations given short prompts. When trained on speech, and without any transcript or annotation, AudioLM generates syntactically and semantically plausible speech continuations while also maintaining speaker identity and prosody for unseen speakers. Furthermore, we demonstrate how our approach extends beyond speech by generating coherent piano music continuations, despite being trained without any symbolic representation of music.

This paper proposes to use low-level spatial features extracted from multichannel audio for sound event detection. We extend the convolutional recurrent neural network to handle more than one type of these multichannel features by learning from each of them separately in the initial stages. We show that instead of concatenating the features of each channel into a single feature vector the network learns sound events in multichannel audio better when they are presented as separate layers of a volume. Using the proposed spatial features over monaural features on the same network gives an absolute F-score improvement of 6.1% on the publicly available TUT-SED 2016 dataset and 2.7% on the TUT-SED 2009 dataset that is fifteen times larger.

Models for audio source separation usually operate on the magnitude spectrum, which ignores phase information and makes separation performance dependant on hyper-parameters for the spectral front-end. Therefore, we investigate end-to-end source separation in the time-domain, which allows modelling phase information and avoids fixed spectral transformations. Due to high sampling rates for audio, employing a long temporal input context on the sample level is difficult, but required for high quality separation results because of long-range temporal correlations. In this context, we propose the Wave-U-Net, an adaptation of the U-Net to the one-dimensional time domain, which repeatedly resamples feature maps to compute and combine features at different time scales. We introduce further architectural improvements, including an output layer that enforces source additivity, an upsampling technique and a context-aware prediction framework to reduce output artifacts. Experiments for singing voice separation indicate that our architecture yields a performance comparable to a state-of-the-art spectrogram-based U-Net architecture, given the same data. Finally, we reveal a problem with outliers in the currently used SDR evaluation metrics and suggest reporting rank-based statistics to alleviate this problem.

We present JASCO, a temporally controlled text-to-music generation model utilizing both symbolic and audio-based conditions. JASCO can generate high-quality music samples conditioned on global text descriptions along with fine-grained local controls. JASCO is based on the Flow Matching modeling paradigm together with a novel conditioning method. This allows music generation controlled both locally (e.g., chords) and globally (text description). Specifically, we apply information bottleneck layers in conjunction with temporal blurring to extract relevant information with respect to specific controls. This allows the incorporation of both symbolic and audio-based conditions in the same text-to-music model. We experiment with various symbolic control signals (e.g., chords, melody), as well as with audio representations (e.g., separated drum tracks, full-mix). We evaluate JASCO considering both generation quality and condition adherence, using both objective metrics and human studies. Results suggest that JASCO is comparable to the evaluated baselines considering generation quality while allowing significantly better and more versatile controls over the generated music. Samples are available on our demo page https://pages.cs.huji.ac.il/adiyoss-lab/JASCO.

Deep learning approaches for black-box modelling of audio effects have shown promise, however, the majority of existing work focuses on nonlinear effects with behaviour on relatively short time-scales, such as guitar amplifiers and distortion. While recurrent and convolutional architectures can theoretically be extended to capture behaviour at longer time scales, we show that simply scaling the width, depth, or dilation factor of existing architectures does not result in satisfactory performance when modelling audio effects such as fuzz and dynamic range compression. To address this, we propose the integration of time-varying feature-wise linear modulation into existing temporal convolutional backbones, an approach that enables learnable adaptation of the intermediate activations. We demonstrate that our approach more accurately captures long-range dependencies for a range of fuzz and compressor implementations across both time and frequency domain metrics. We provide sound examples, source code, and pretrained models to faciliate reproducibility.

Audio is an essential part of our life, but creating it often requires expertise and is time-consuming. Research communities have made great progress over the past year advancing the performance of large scale audio generative models for a single modality (speech, sound, or music) through adopting more powerful generative models and scaling data. However, these models lack controllability in several aspects: speech generation models cannot synthesize novel styles based on text description and are limited on domain coverage such as outdoor environments; sound generation models only provide coarse-grained control based on descriptions like "a person speaking" and would only generate mumbling human voices. This paper presents Audiobox, a unified model based on flow-matching that is capable of generating various audio modalities. We design description-based and example-based prompting to enhance controllability and unify speech and sound generation paradigms. We allow transcript, vocal, and other audio styles to be controlled independently when generating speech. To improve model generalization with limited labels, we adapt a self-supervised infilling objective to pre-train on large quantities of unlabeled audio. Audiobox sets new benchmarks on speech and sound generation (0.745 similarity on Librispeech for zero-shot TTS; 0.77 FAD on AudioCaps for text-to-sound) and unlocks new methods for generating audio with novel vocal and acoustic styles. We further integrate Bespoke Solvers, which speeds up generation by over 25 times compared to the default ODE solver for flow-matching, without loss of performance on several tasks. Our demo is available at https://audiobox.metademolab.com/

In language modeling based music generation, a generated waveform is represented by a sequence of hierarchical token stacks that can be decoded either in an auto-regressive manner or in parallel, depending on the codebook patterns. In particular, flattening the codebooks represents the highest quality decoding strategy, while being notoriously slow. To this end, we propose a novel stack-and-delay style of decoding strategy to improve upon the flat pattern decoding where generation speed is four times faster as opposed to vanilla flat decoding. This brings the inference time close to that of the delay decoding strategy, and allows for faster inference on GPU for small batch sizes. For the same inference efficiency budget as the delay pattern, we show that the proposed approach performs better in objective evaluations, almost closing the gap with the flat pattern in terms of quality. The results are corroborated by subjective evaluations which show that samples generated by the new model are slightly more often preferred to samples generated by the competing model given the same text prompts.

Large language models (LLMs) prompted with text and audio represent the state of the art in various auditory tasks, including speech, music, and general audio, showing emergent abilities on unseen tasks. However, these capabilities have yet to be fully demonstrated in bioacoustics tasks, such as detecting animal vocalizations in large recordings, classifying rare and endangered species, and labeling context and behavior - tasks that are crucial for conservation, biodiversity monitoring, and the study of animal behavior. In this work, we present NatureLM-audio, the first audio-language foundation model specifically designed for bioacoustics. Our carefully curated training dataset comprises text-audio pairs spanning a diverse range of bioacoustics, speech, and music data, designed to address the challenges posed by limited annotated datasets in the field. We demonstrate successful transfer of learned representations from music and speech to bioacoustics, and our model shows promising generalization to unseen taxa and tasks. Importantly, we test NatureLM-audio on a novel benchmark (BEANS-Zero) and it sets the new state of the art (SotA) on several bioacoustics tasks, including zero-shot classification of unseen species. To advance bioacoustics research, we also open-source the code for generating training and benchmark data, as well as for training the model.

Conditional sound separation in multi-source audio mixtures without having access to single source sound data during training is a long standing challenge. Existing mix-and-separate based methods suffer from significant performance drop with multi-source training mixtures due to the lack of supervision signal for single source separation cases during training. However, in the case of language-conditional audio separation, we do have access to corresponding text descriptions for each audio mixture in our training data, which can be seen as (rough) representations of the audio samples in the language modality. To this end, in this paper, we propose a generic bi-modal separation framework which can enhance the existing unsupervised frameworks to separate single-source signals in a target modality (i.e., audio) using the easily separable corresponding signals in the conditioning modality (i.e., language), without having access to single-source samples in the target modality during training. We empirically show that this is well within reach if we have access to a pretrained joint embedding model between the two modalities (i.e., CLAP). Furthermore, we propose to incorporate our framework into two fundamental scenarios to enhance separation performance. First, we show that our proposed methodology significantly improves the performance of purely unsupervised baselines by reducing the distribution shift between training and test samples. In particular, we show that our framework can achieve 71% boost in terms of Signal-to-Distortion Ratio (SDR) over the baseline, reaching 97.5% of the supervised learning performance. Second, we show that we can further improve the performance of the supervised learning itself by 17% if we augment it by our proposed weakly-supervised framework, that enables a powerful semi-supervised framework for audio separation.

The massive growth of self-supervised learning (SSL) has been witnessed in language, vision, speech, and audio domains over the past few years. While discrete label prediction is widely adopted for other modalities, the state-of-the-art audio SSL models still employ reconstruction loss for pre-training. Compared with reconstruction loss, semantic-rich discrete label prediction encourages the SSL model to abstract the high-level audio semantics and discard the redundant details as in human perception. However, a semantic-rich acoustic tokenizer for general audio pre-training is usually not straightforward to obtain, due to the continuous property of audio and unavailable phoneme sequences like speech. To tackle this challenge, we propose BEATs, an iterative audio pre-training framework to learn Bidirectional Encoder representation from Audio Transformers, where an acoustic tokenizer and an audio SSL model are optimized by iterations. In the first iteration, we use random projection as the acoustic tokenizer to train an audio SSL model in a mask and label prediction manner. Then, we train an acoustic tokenizer for the next iteration by distilling the semantic knowledge from the pre-trained or fine-tuned audio SSL model. The iteration is repeated with the hope of mutual promotion of the acoustic tokenizer and audio SSL model. The experimental results demonstrate our acoustic tokenizers can generate discrete labels with rich audio semantics and our audio SSL models achieve state-of-the-art results across various audio classification benchmarks, even outperforming previous models that use more training data and model parameters significantly. Specifically, we set a new state-of-the-art mAP 50.6% on AudioSet-2M for audio-only models without using any external data, and 98.1% accuracy on ESC-50. The code and pre-trained models are available at https://aka.ms/beats.

We introduce SPEAR-TTS, a multi-speaker text-to-speech (TTS) system that can be trained with minimal supervision. By combining two types of discrete speech representations, we cast TTS as a composition of two sequence-to-sequence tasks: from text to high-level semantic tokens (akin to "reading") and from semantic tokens to low-level acoustic tokens ("speaking"). Decoupling these two tasks enables training of the "speaking" module using abundant audio-only data, and unlocks the highly efficient combination of pretraining and backtranslation to reduce the need for parallel data when training the "reading" component. To control the speaker identity, we adopt example prompting, which allows SPEAR-TTS to generalize to unseen speakers using only a short sample of 3 seconds, without any explicit speaker representation or speaker-id labels. Our experiments demonstrate that SPEAR-TTS achieves a character error rate that is competitive with state-of-the-art methods using only 15 minutes of parallel data, while matching ground-truth speech in terms of naturalness and acoustic quality, as measured in subjective tests.

We propose a learnable content adaptive front end for audio signal processing. Before the modern advent of deep learning, we used fixed representation non-learnable front-ends like spectrogram or mel-spectrogram with/without neural architectures. With convolutional architectures supporting various applications such as ASR and acoustic scene understanding, a shift to a learnable front ends occurred in which both the type of basis functions and the weight were learned from scratch and optimized for the particular task of interest. With the shift to transformer-based architectures with no convolutional blocks present, a linear layer projects small waveform patches onto a small latent dimension before feeding them to a transformer architecture. In this work, we propose a way of computing a content-adaptive learnable time-frequency representation. We pass each audio signal through a bank of convolutional filters, each giving a fixed-dimensional vector. It is akin to learning a bank of finite impulse-response filterbanks and passing the input signal through the optimum filter bank depending on the content of the input signal. A content-adaptive learnable time-frequency representation may be more broadly applicable, beyond the experiments in this paper.

In this paper, we propose and investigate the use of neural audio codec language models for the automatic generation of sample-based musical instruments based on text or reference audio prompts. Our approach extends a generative audio framework to condition on pitch across an 88-key spectrum, velocity, and a combined text/audio embedding. We identify maintaining timbral consistency within the generated instruments as a major challenge. To tackle this issue, we introduce three distinct conditioning schemes. We analyze our methods through objective metrics and human listening tests, demonstrating that our approach can produce compelling musical instruments. Specifically, we introduce a new objective metric to evaluate the timbral consistency of the generated instruments and adapt the average Contrastive Language-Audio Pretraining (CLAP) score for the text-to-instrument case, noting that its naive application is unsuitable for assessing this task. Our findings reveal a complex interplay between timbral consistency, the quality of generated samples, and their correspondence to the input prompt.

In recent Text-to-Speech (TTS) systems, a neural vocoder often generates speech samples by solely conditioning on acoustic features predicted from an acoustic model. However, there are always distortions existing in the predicted acoustic features, compared to those of the groundtruth, especially in the common case of poor acoustic modeling due to low-quality training data. To overcome such limits, we propose a Self-supervised learning framework to learn an Anti-distortion acoustic Representation (SAR) to replace human-crafted acoustic features by introducing distortion prior to an auto-encoder pre-training process. The learned acoustic representation from the proposed framework is proved anti-distortion compared to the most commonly used mel-spectrogram through both objective and subjective evaluation.

Large language models (LLMs) have achieved remarkable success in the field of natural language processing, enabling better human-computer interaction using natural language. However, the seamless integration of speech signals into LLMs has not been explored well. The "decoder-only" architecture has also not been well studied for speech processing tasks. In this research, we introduce Speech-LLaMA, a novel approach that effectively incorporates acoustic information into text-based large language models. Our method leverages Connectionist Temporal Classification and a simple audio encoder to map the compressed acoustic features to the continuous semantic space of the LLM. In addition, we further probe the decoder-only architecture for speech-to-text tasks by training a smaller scale randomly initialized speech-LLaMA model from speech-text paired data alone. We conduct experiments on multilingual speech-to-text translation tasks and demonstrate a significant improvement over strong baselines, highlighting the potential advantages of decoder-only models for speech-to-text conversion.

Sequence-to-sequence attention-based models on subword units allow simple open-vocabulary end-to-end speech recognition. In this work, we show that such models can achieve competitive results on the Switchboard 300h and LibriSpeech 1000h tasks. In particular, we report the state-of-the-art word error rates (WER) of 3.54% on the dev-clean and 3.82% on the test-clean evaluation subsets of LibriSpeech. We introduce a new pretraining scheme by starting with a high time reduction factor and lowering it during training, which is crucial both for convergence and final performance. In some experiments, we also use an auxiliary CTC loss function to help the convergence. In addition, we train long short-term memory (LSTM) language models on subword units. By shallow fusion, we report up to 27% relative improvements in WER over the attention baseline without a language model.

Denoising diffusion probabilistic models (DDPMs) have recently achieved leading performances in many generative tasks. However, the inherited iterative sampling process costs hindered their applications to speech synthesis. This paper proposes FastDiff, a fast conditional diffusion model for high-quality speech synthesis. FastDiff employs a stack of time-aware location-variable convolutions of diverse receptive field patterns to efficiently model long-term time dependencies with adaptive conditions. A noise schedule predictor is also adopted to reduce the sampling steps without sacrificing the generation quality. Based on FastDiff, we design an end-to-end text-to-speech synthesizer, FastDiff-TTS, which generates high-fidelity speech waveforms without any intermediate feature (e.g., Mel-spectrogram). Our evaluation of FastDiff demonstrates the state-of-the-art results with higher-quality (MOS 4.28) speech samples. Also, FastDiff enables a sampling speed of 58x faster than real-time on a V100 GPU, making diffusion models practically applicable to speech synthesis deployment for the first time. We further show that FastDiff generalized well to the mel-spectrogram inversion of unseen speakers, and FastDiff-TTS outperformed other competing methods in end-to-end text-to-speech synthesis. Audio samples are available at https://FastDiff.github.io/.

In the domain of audio processing, Transfer Learning has facilitated the rise of Self-Supervised Learning and Zero-Shot Learning techniques. These approaches have led to the development of versatile models capable of tackling a wide array of tasks, while delivering state-of-the-art performance. However, current models inherently lack the capacity to produce the requisite language for open-ended tasks, such as Audio Captioning or Audio Question & Answering. We introduce Pengi, a novel Audio Language Model that leverages Transfer Learning by framing all audio tasks as text-generation tasks. It takes as input, an audio recording, and text, and generates free-form text as output. The input audio is represented as a sequence of continuous embeddings by an audio encoder. A text encoder does the same for the corresponding text input. Both sequences are combined as a prefix to prompt a pre-trained frozen language model. The unified architecture of Pengi enables open-ended tasks and close-ended tasks without any additional fine-tuning or task-specific extensions. When evaluated on 22 downstream tasks, our approach yields state-of-the-art performance in several of them. Our results show that connecting language models with audio models is a major step towards general-purpose audio understanding

Language-queried audio source separation (LASS) is a new paradigm for computational auditory scene analysis (CASA). LASS aims to separate a target sound from an audio mixture given a natural language query, which provides a natural and scalable interface for digital audio applications. Recent works on LASS, despite attaining promising separation performance on specific sources (e.g., musical instruments, limited classes of audio events), are unable to separate audio concepts in the open domain. In this work, we introduce AudioSep, a foundation model for open-domain audio source separation with natural language queries. We train AudioSep on large-scale multimodal datasets and extensively evaluate its capabilities on numerous tasks including audio event separation, musical instrument separation, and speech enhancement. AudioSep demonstrates strong separation performance and impressive zero-shot generalization ability using audio captions or text labels as queries, substantially outperforming previous audio-queried and language-queried sound separation models. For reproducibility of this work, we will release the source code, evaluation benchmark and pre-trained model at: https://github.com/Audio-AGI/AudioSep.

Automatic transcriptions of consumer-generated multi-media content such as "Youtube" videos still exhibit high word error rates. Such data typically occupies a very broad domain, has been recorded in challenging conditions, with cheap hardware and a focus on the visual modality, and may have been post-processed or edited. In this paper, we extend our earlier work on adapting the acoustic model of a DNN-based speech recognition system to an RNN language model and show how both can be adapted to the objects and scenes that can be automatically detected in the video. We are working on a corpus of "how-to" videos from the web, and the idea is that an object that can be seen ("car"), or a scene that is being detected ("kitchen") can be used to condition both models on the "context" of the recording, thereby reducing perplexity and improving transcription. We achieve good improvements in both cases and compare and analyze the respective reductions in word error rate. We expect that our results can be used for any type of speech processing in which "context" information is available, for example in robotics, man-machine interaction, or when indexing large audio-visual archives, and should ultimately help to bring together the "video-to-text" and "speech-to-text" communities.

We present a novel multi-modal unspoken punctuation prediction system for the English language which combines acoustic and text features. We demonstrate for the first time, that by relying exclusively on synthetic data generated using a prosody-aware text-to-speech system, we can outperform a model trained with expensive human audio recordings on the unspoken punctuation prediction problem. Our model architecture is well suited for on-device use. This is achieved by leveraging hash-based embeddings of automatic speech recognition text output in conjunction with acoustic features as input to a quasi-recurrent neural network, keeping the model size small and latency low.

This report presents the dataset and the evaluation setup of the Sound Event Localization & Detection (SELD) task for the DCASE 2020 Challenge. The SELD task refers to the problem of trying to simultaneously classify a known set of sound event classes, detect their temporal activations, and estimate their spatial directions or locations while they are active. To train and test SELD systems, datasets of diverse sound events occurring under realistic acoustic conditions are needed. Compared to the previous challenge, a significantly more complex dataset was created for DCASE 2020. The two key differences are a more diverse range of acoustical conditions, and dynamic conditions, i.e. moving sources. The spatial sound scenes are created using real room impulse responses captured in a continuous manner with a slowly moving excitation source. Both static and moving sound events are synthesized from them. Ambient noise recorded on location is added to complete the generation of scene recordings. A baseline SELD method accompanies the dataset, based on a convolutional recurrent neural network, to provide benchmark scores for the task. The baseline is an updated version of the one used in the previous challenge, with input features and training modifications to improve its performance.

We propose Citrinet - a new end-to-end convolutional Connectionist Temporal Classification (CTC) based automatic speech recognition (ASR) model. Citrinet is deep residual neural model which uses 1D time-channel separable convolutions combined with sub-word encoding and squeeze-and-excitation. The resulting architecture significantly reduces the gap between non-autoregressive and sequence-to-sequence and transducer models. We evaluate Citrinet on LibriSpeech, TED-LIUM2, AISHELL-1 and Multilingual LibriSpeech (MLS) English speech datasets. Citrinet accuracy on these datasets is close to the best autoregressive Transducer models.

Continuous speech separation for meeting pre-processing has recently become a focused research topic. Compared to the data in utterance-level speech separation, the meeting-style audio stream lasts longer, has an uncertain number of speakers. We adopt the time-domain speech separation method and the recently proposed Graph-PIT to build a super low-latency online speech separation model, which is very important for the real application. The low-latency time-domain encoder with a small stride leads to an extremely long feature sequence. We proposed a simple yet efficient model named Skipping Memory (SkiM) for the long sequence modeling. Experimental results show that SkiM achieves on par or even better separation performance than DPRNN. Meanwhile, the computational cost of SkiM is reduced by 75% compared to DPRNN. The strong long sequence modeling capability and low computational cost make SkiM a suitable model for online CSS applications. Our fastest real-time model gets 17.1 dB signal-to-distortion (SDR) improvement with less than 1-millisecond latency in the simulated meeting-style evaluation.

In this paper, we propose an efficient and accurate streaming speech recognition model based on the FastConformer architecture. We adapted the FastConformer architecture for streaming applications through: (1) constraining both the look-ahead and past contexts in the encoder, and (2) introducing an activation caching mechanism to enable the non-autoregressive encoder to operate autoregressively during inference. The proposed model is thoughtfully designed in a way to eliminate the accuracy disparity between the train and inference time which is common for many streaming models. Furthermore, our proposed encoder works with various decoder configurations including Connectionist Temporal Classification (CTC) and RNN-Transducer (RNNT) decoders. Additionally, we introduced a hybrid CTC/RNNT architecture which utilizes a shared encoder with both a CTC and RNNT decoder to boost the accuracy and save computation. We evaluate the proposed model on LibriSpeech dataset and a multi-domain large scale dataset and demonstrate that it can achieve better accuracy with lower latency and inference time compared to a conventional buffered streaming model baseline. We also showed that training a model with multiple latencies can achieve better accuracy than single latency models while it enables us to support multiple latencies with a single model. Our experiments also showed the hybrid architecture would not only speedup the convergence of the CTC decoder but also improves the accuracy of streaming models compared to single decoder models.

We study the capabilities of speech processing systems trained simply to predict large amounts of transcripts of audio on the internet. When scaled to 680,000 hours of multilingual and multitask supervision, the resulting models generalize well to standard benchmarks and are often competitive with prior fully supervised results but in a zero-shot transfer setting without the need for any fine-tuning. When compared to humans, the models approach their accuracy and robustness. We are releasing models and inference code to serve as a foundation for further work on robust speech processing.

The past decade has witnessed significant advances in time series modeling with deep learning. While achieving state-of-the-art results, the best-performing architectures vary highly across applications and domains. Meanwhile, for natural language processing, the Generative Pre-trained Transformer (GPT) has demonstrated impressive performance via training one general-purpose model across various textual datasets. It is intriguing to explore whether GPT-type architectures can be effective for time series, capturing the intrinsic dynamic attributes and leading to significant accuracy improvements. In this paper, we propose a novel framework, TEMPO, that can effectively learn time series representations. We focus on utilizing two essential inductive biases of the time series task for pre-trained models: (i) decomposition of the complex interaction between trend, seasonal and residual components; and (ii) introducing the selection-based prompts to facilitate distribution adaptation in non-stationary time series. TEMPO expands the capability for dynamically modeling real-world temporal phenomena from data within diverse domains. Our experiments demonstrate the superior performance of TEMPO over state-of-the-art methods on a number of time series benchmark datasets. This performance gain is observed not only in standard supervised learning settings but also in scenarios involving previously unseen datasets as well as in scenarios with multi-modal inputs. This compelling finding highlights TEMPO's potential to constitute a foundational model-building framework.

Progress in speech processing has been facilitated by shared datasets and benchmarks. Historically these have focused on automatic speech recognition (ASR), speaker identification, or other lower-level tasks. Interest has been growing in higher-level spoken language understanding tasks, including using end-to-end models, but there are fewer annotated datasets for such tasks. At the same time, recent work shows the possibility of pre-training generic representations and then fine-tuning for several tasks using relatively little labeled data. We propose to create a suite of benchmark tasks for Spoken Language Understanding Evaluation (SLUE) consisting of limited-size labeled training sets and corresponding evaluation sets. This resource would allow the research community to track progress, evaluate pre-trained representations for higher-level tasks, and study open questions such as the utility of pipeline versus end-to-end approaches. We present the first phase of the SLUE benchmark suite, consisting of named entity recognition, sentiment analysis, and ASR on the corresponding datasets. We focus on naturally produced (not read or synthesized) speech, and freely available datasets. We provide new transcriptions and annotations on subsets of the VoxCeleb and VoxPopuli datasets, evaluation metrics and results for baseline models, and an open-source toolkit to reproduce the baselines and evaluate new models.

The ability to automatically generate music that appropriately matches an arbitrary input track is a challenging task. We present a novel controllable system for generating single stems to accompany musical mixes of arbitrary length. At the core of our method are audio autoencoders that efficiently compress audio waveform samples into invertible latent representations, and a conditional latent diffusion model that takes as input the latent encoding of a mix and generates the latent encoding of a corresponding stem. To provide control over the timbre of generated samples, we introduce a technique to ground the latent space to a user-provided reference style during diffusion sampling. For further improving audio quality, we adapt classifier-free guidance to avoid distortions at high guidance strengths when generating an unbounded latent space. We train our model on a dataset of pairs of mixes and matching bass stems. Quantitative experiments demonstrate that, given an input mix, the proposed system can generate basslines with user-specified timbres. Our controllable conditional audio generation framework represents a significant step forward in creating generative AI tools to assist musicians in music production.

We introduce Seed-TTS, a family of large-scale autoregressive text-to-speech (TTS) models capable of generating speech that is virtually indistinguishable from human speech. Seed-TTS serves as a foundation model for speech generation and excels in speech in-context learning, achieving performance in speaker similarity and naturalness that matches ground truth human speech in both objective and subjective evaluations. With fine-tuning, we achieve even higher subjective scores across these metrics. Seed-TTS offers superior controllability over various speech attributes such as emotion and is capable of generating highly expressive and diverse speech for speakers in the wild. Furthermore, we propose a self-distillation method for speech factorization, as well as a reinforcement learning approach to enhance model robustness, speaker similarity, and controllability. We additionally present a non-autoregressive (NAR) variant of the Seed-TTS model, named Seed-TTS_DiT, which utilizes a fully diffusion-based architecture. Unlike previous NAR-based TTS systems, Seed-TTS_DiT does not depend on pre-estimated phoneme durations and performs speech generation through end-to-end processing. We demonstrate that this variant achieves comparable performance to the language model-based variant and showcase its effectiveness in speech editing. We encourage readers to listen to demos at https://bytedancespeech.github.io/seedtts_tech_report.

In this paper, we introduce a novel language identification system based on conformer layers. We propose an attentive temporal pooling mechanism to allow the model to carry information in long-form audio via a recurrent form, such that the inference can be performed in a streaming fashion. Additionally, we investigate two domain adaptation approaches to allow adapting an existing language identification model without retraining the model parameters for a new domain. We perform a comparative study of different model topologies under different constraints of model size, and find that conformer-based models significantly outperform LSTM and transformer based models. Our experiments also show that attentive temporal pooling and domain adaptation improve model accuracy.

This paper introduces ESPnet-SPK, a toolkit designed with several objectives for training speaker embedding extractors. First, we provide an open-source platform for researchers in the speaker recognition community to effortlessly build models. We provide several models, ranging from x-vector to recent SKA-TDNN. Through the modularized architecture design, variants can be developed easily. We also aspire to bridge developed models with other domains, facilitating the broad research community to effortlessly incorporate state-of-the-art embedding extractors. Pre-trained embedding extractors can be accessed in an off-the-shelf manner and we demonstrate the toolkit's versatility by showcasing its integration with two tasks. Another goal is to integrate with diverse self-supervised learning features. We release a reproducible recipe that achieves an equal error rate of 0.39% on the Vox1-O evaluation protocol using WavLM-Large with ECAPA-TDNN.

In this work, we build a simple but strong baseline for sounding video generation. Given base diffusion models for audio and video, we integrate them with additional modules into a single model and train it to make the model jointly generate audio and video. To enhance alignment between audio-video pairs, we introduce two novel mechanisms in our model. The first one is timestep adjustment, which provides different timestep information to each base model. It is designed to align how samples are generated along with timesteps across modalities. The second one is a new design of the additional modules, termed Cross-Modal Conditioning as Positional Encoding (CMC-PE). In CMC-PE, cross-modal information is embedded as if it represents temporal position information, and the embeddings are fed into the model like positional encoding. Compared with the popular cross-attention mechanism, CMC-PE provides a better inductive bias for temporal alignment in the generated data. Experimental results validate the effectiveness of the two newly introduced mechanisms and also demonstrate that our method outperforms existing methods.

This paper proposes a neural network architecture and training scheme to learn the start and end time of sound events (strong labels) in an audio recording given just the list of sound events existing in the audio without time information (weak labels). We achieve this by using a stacked convolutional and recurrent neural network with two prediction layers in sequence one for the strong followed by the weak label. The network is trained using frame-wise log mel-band energy as the input audio feature, and weak labels provided in the dataset as labels for the weak label prediction layer. Strong labels are generated by replicating the weak labels as many number of times as the frames in the input audio feature, and used for strong label layer during training. We propose to control what the network learns from the weak and strong labels by different weighting for the loss computed in the two prediction layers. The proposed method is evaluated on a publicly available dataset of 155 hours with 17 sound event classes. The method achieves the best error rate of 0.84 for strong labels and F-score of 43.3% for weak labels on the unseen test split.

Music has a unique and complex structure which is challenging for both expert humans and existing AI systems to understand, and presents unique challenges relative to other forms of audio. We present LLark, an instruction-tuned multimodal model for music understanding. We detail our process for dataset creation, which involves augmenting the annotations of diverse open-source music datasets and converting them to a unified instruction-tuning format. We propose a multimodal architecture for LLark, integrating a pretrained generative model for music with a pretrained language model. In evaluations on three types of tasks (music understanding, captioning, and reasoning), we show that our model matches or outperforms existing baselines in zero-shot generalization for music understanding, and that humans show a high degree of agreement with the model's responses in captioning and reasoning tasks. LLark is trained entirely from open-source music data and models, and we make our training code available along with the release of this paper. Additional results and audio examples are at https://bit.ly/llark, and our source code is available at https://github.com/spotify-research/llark .

While recent advancements in speech language models have achieved significant progress, they face remarkable challenges in modeling the long acoustic sequences of neural audio codecs. In this paper, we introduce Generative Pre-trained Speech Transformer (GPST), a hierarchical transformer designed for efficient speech language modeling. GPST quantizes audio waveforms into two distinct types of discrete speech representations and integrates them within a hierarchical transformer architecture, allowing for a unified one-stage generation process and enhancing Hi-Res audio generation capabilities. By training on large corpora of speeches in an end-to-end unsupervised manner, GPST can generate syntactically consistent speech with diverse speaker identities. Given a brief 3-second prompt, GPST can produce natural and coherent personalized speech, demonstrating in-context learning abilities. Moreover, our approach can be easily extended to spoken cross-lingual speech generation by incorporating multi-lingual semantic tokens and universal acoustic tokens. Experimental results indicate that GPST significantly outperforms the existing speech language models in terms of word error rate, speech quality, and speaker similarity. See https://youngsheen.github.io/GPST/demo for demo samples.

This paper presents VoiceLDM, a model designed to produce audio that accurately follows two distinct natural language text prompts: the description prompt and the content prompt. The former provides information about the overall environmental context of the audio, while the latter conveys the linguistic content. To achieve this, we adopt a text-to-audio (TTA) model based on latent diffusion models and extend its functionality to incorporate an additional content prompt as a conditional input. By utilizing pretrained contrastive language-audio pretraining (CLAP) and Whisper, VoiceLDM is trained on large amounts of real-world audio without manual annotations or transcriptions. Additionally, we employ dual classifier-free guidance to further enhance the controllability of VoiceLDM. Experimental results demonstrate that VoiceLDM is capable of generating plausible audio that aligns well with both input conditions, even surpassing the speech intelligibility of the ground truth audio on the AudioCaps test set. Furthermore, we explore the text-to-speech (TTS) and zero-shot text-to-audio capabilities of VoiceLDM and show that it achieves competitive results. Demos and code are available at https://voiceldm.github.io.

Non-autoregressive automatic speech recognition (ASR) modeling has received increasing attention recently because of its fast decoding speed and superior performance. Among representatives, methods based on the connectionist temporal classification (CTC) are still a dominating stream. However, the theoretically inherent flaw, the assumption of independence between tokens, creates a performance barrier for the school of works. To mitigate the challenge, we propose a context-aware knowledge transferring strategy, consisting of a knowledge transferring module and a context-aware training strategy, for CTC-based ASR. The former is designed to distill linguistic information from a pre-trained language model, and the latter is framed to modulate the limitations caused by the conditional independence assumption. As a result, a knowledge-injected context-aware CTC-based ASR built upon the wav2vec2.0 is presented in this paper. A series of experiments on the AISHELL-1 and AISHELL-2 datasets demonstrate the effectiveness of the proposed method.

Neural text-to-speech (TTS) has achieved human-like synthetic speech for single-speaker, single-language synthesis. Multilingual TTS systems are limited to resource-rich languages due to the lack of large paired text and studio-quality audio data. In most cases, TTS systems are built using a single speaker's voice. However, there is growing interest in developing systems that can synthesize voices for new speakers using only a few seconds of their speech. This paper presents ZMM-TTS, a multilingual and multispeaker framework utilizing quantized latent speech representations from a large-scale, pre-trained, self-supervised model. Our paper is the first to incorporate the representations from text-based and speech-based self-supervised learning models into multilingual speech synthesis tasks. We conducted comprehensive subjective and objective evaluations through a series of experiments. Our model has been proven effective in terms of speech naturalness and similarity for both seen and unseen speakers in six high-resource languages. We also tested the efficiency of our method on two hypothetical low-resource languages. The results are promising, indicating that our proposed approach can synthesize audio that is intelligible and has a high degree of similarity to the target speaker's voice, even without any training data for the new, unseen language.

Playlists have become a significant part of our listening experience because of the digital cloud-based services such as Spotify, Pandora, Apple Music. Owing to the meteoric rise in the usage of playlists, recommending playlists is crucial to music services today. Although there has been a lot of work done in playlist prediction, the area of playlist representation hasn't received that level of attention. Over the last few years, sequence-to-sequence models, especially in the field of natural language processing, have shown the effectiveness of learned embeddings in capturing the semantic characteristics of sequences. We can apply similar concepts to music to learn fixed length representations for playlists and use those representations for downstream tasks such as playlist discovery, browsing, and recommendation. In this work, we formulate the problem of learning a fixed-length playlist representation in an unsupervised manner, using Sequence-to-sequence (Seq2seq) models, interpreting playlists as sentences and songs as words. We compare our model with two other encoding architectures for baseline comparison. We evaluate our work using the suite of tasks commonly used for assessing sentence embeddings, along with a few additional tasks pertaining to music, and a recommendation task to study the traits captured by the playlist embeddings and their effectiveness for the purpose of music recommendation.

Recently, audio generation tasks have attracted considerable research interests. Precise temporal controllability is essential to integrate audio generation with real applications. In this work, we propose a temporal controlled audio generation framework, PicoAudio. PicoAudio integrates temporal information to guide audio generation through tailored model design. It leverages data crawling, segmentation, filtering, and simulation of fine-grained temporally-aligned audio-text data. Both subjective and objective evaluations demonstrate that PicoAudio dramantically surpasses current state-of-the-art generation models in terms of timestamp and occurrence frequency controllability. The generated samples are available on the demo website https://PicoAudio.github.io.

This paper introduces the idea of applying signal processing inside a Large Language Model (LLM). With the recent explosion of generative AI, our work can help bridge two fields together, namely the field of signal processing and large language models. We draw parallels between classical Fourier-Transforms and Fourier Transform-like learnable time-frequency representations for every intermediate activation signal of an LLM. Once we decompose every activation signal across tokens into a time-frequency representation, we learn how to filter and reconstruct them, with all components learned from scratch, to predict the next token given the previous context. We show that for GPT-like architectures, our work achieves faster convergence and significantly increases performance by adding a minuscule number of extra parameters when trained for the same epochs. We hope this work paves the way for algorithms exploring signal processing inside the signals found in neural architectures like LLMs and beyond.

This paper introduces FunASR, an open-source speech recognition toolkit designed to bridge the gap between academic research and industrial applications. FunASR offers models trained on large-scale industrial corpora and the ability to deploy them in applications. The toolkit's flagship model, Paraformer, is a non-autoregressive end-to-end speech recognition model that has been trained on a manually annotated Mandarin speech recognition dataset that contains 60,000 hours of speech. To improve the performance of Paraformer, we have added timestamp prediction and hotword customization capabilities to the standard Paraformer backbone. In addition, to facilitate model deployment, we have open-sourced a voice activity detection model based on the Feedforward Sequential Memory Network (FSMN-VAD) and a text post-processing punctuation model based on the controllable time-delay Transformer (CT-Transformer), both of which were trained on industrial corpora. These functional modules provide a solid foundation for building high-precision long audio speech recognition services. Compared to other models trained on open datasets, Paraformer demonstrates superior performance.

We introduce Noise2Music, where a series of diffusion models is trained to generate high-quality 30-second music clips from text prompts. Two types of diffusion models, a generator model, which generates an intermediate representation conditioned on text, and a cascader model, which generates high-fidelity audio conditioned on the intermediate representation and possibly the text, are trained and utilized in succession to generate high-fidelity music. We explore two options for the intermediate representation, one using a spectrogram and the other using audio with lower fidelity. We find that the generated audio is not only able to faithfully reflect key elements of the text prompt such as genre, tempo, instruments, mood, and era, but goes beyond to ground fine-grained semantics of the prompt. Pretrained large language models play a key role in this story -- they are used to generate paired text for the audio of the training set and to extract embeddings of the text prompts ingested by the diffusion models. Generated examples: https://google-research.github.io/noise2music

Transformers have been the most successful architecture for various speech modeling tasks, including speech separation. However, the self-attention mechanism in transformers with quadratic complexity is inefficient in computation and memory. Recent models incorporate new layers and modules along with transformers for better performance but also introduce extra model complexity. In this work, we replace transformers with Mamba, a selective state space model, for speech separation. We propose dual-path Mamba, which models short-term and long-term forward and backward dependency of speech signals using selective state spaces. Our experimental results on the WSJ0-2mix data show that our dual-path Mamba models of comparably smaller sizes outperform state-of-the-art RNN model DPRNN, CNN model WaveSplit, and transformer model Sepformer. Code: https://github.com/xi-j/Mamba-TasNet

Automatic Music Transcription (AMT) has been recognized as a key enabling technology with a wide range of applications. Given the task's complexity, best results have typically been reported for systems focusing on specific settings, e.g. instrument-specific systems tend to yield improved results over instrument-agnostic methods. Similarly, higher accuracy can be obtained when only estimating frame-wise f_0 values and neglecting the harder note event detection. Despite their high accuracy, such specialized systems often cannot be deployed in the real-world. Storage and network constraints prohibit the use of multiple specialized models, while memory and run-time constraints limit their complexity. In this paper, we propose a lightweight neural network for musical instrument transcription, which supports polyphonic outputs and generalizes to a wide variety of instruments (including vocals). Our model is trained to jointly predict frame-wise onsets, multipitch and note activations, and we experimentally show that this multi-output structure improves the resulting frame-level note accuracy. Despite its simplicity, benchmark results show our system's note estimation to be substantially better than a comparable baseline, and its frame-level accuracy to be only marginally below those of specialized state-of-the-art AMT systems. With this work we hope to encourage the community to further investigate low-resource, instrument-agnostic AMT systems.

We introduce KALL-E, a novel autoregressive (AR) language modeling approach with next-distribution prediction for text-to-speech (TTS) synthesis. Unlike existing methods, KALL-E directly models and predicts the continuous speech distribution conditioned on text without relying on VAE- or diffusion-based components. Specifically, we use WaveVAE to extract continuous speech distributions from waveforms instead of using discrete speech tokens. A single AR language model predicts these continuous speech distributions from text, with a Kullback-Leibler divergence loss as the constraint. Experimental results show that KALL-E outperforms open-source implementations of YourTTS, VALL-E, NaturalSpeech 2, and CosyVoice in terms of naturalness and speaker similarity in zero-shot TTS scenarios. Moreover, KALL-E demonstrates exceptional zero-shot capabilities in emotion and accent cloning. Importantly, KALL-E presents a more straightforward and effective paradigm for using continuous speech representations in TTS. Audio samples are available at: https://zxf-icpc.github.io/kalle/.

This paper presents an innovative approach to enhance control over audio generation by emphasizing the alignment between audio and text representations during model training. In the context of language model-based audio generation, the model leverages input from both textual and audio token representations to predict subsequent audio tokens. However, the current configuration lacks explicit regularization to ensure the alignment between the chosen text representation and the language model's predictions. Our proposal involves the incorporation of audio and text representation regularization, particularly during the classifier-free guidance (CFG) phase, where the text condition is excluded from cross attention during language model training. The aim of this proposed representation regularization is to minimize discrepancies in audio and text similarity compared to other samples within the same training batch. Experimental results on both music and audio generation tasks demonstrate that our proposed methods lead to improvements in objective metrics for both audio and music generation, as well as an enhancement in the human perception for audio generation.

We propose a new end-to-end neural acoustic model for automatic speech recognition. The model is composed of multiple blocks with residual connections between them. Each block consists of one or more modules with 1D time-channel separable convolutional layers, batch normalization, and ReLU layers. It is trained with CTC loss. The proposed network achieves near state-of-the-art accuracy on LibriSpeech and Wall Street Journal, while having fewer parameters than all competing models. We also demonstrate that this model can be effectively fine-tuned on new datasets.

Single-channel, speaker-independent speech separation methods have recently seen great progress. However, the accuracy, latency, and computational cost of such methods remain insufficient. The majority of the previous methods have formulated the separation problem through the time-frequency representation of the mixed signal, which has several drawbacks, including the decoupling of the phase and magnitude of the signal, the suboptimality of time-frequency representation for speech separation, and the long latency in calculating the spectrograms. To address these shortcomings, we propose a fully-convolutional time-domain audio separation network (Conv-TasNet), a deep learning framework for end-to-end time-domain speech separation. Conv-TasNet uses a linear encoder to generate a representation of the speech waveform optimized for separating individual speakers. Speaker separation is achieved by applying a set of weighting functions (masks) to the encoder output. The modified encoder representations are then inverted back to the waveforms using a linear decoder. The masks are found using a temporal convolutional network (TCN) consisting of stacked 1-D dilated convolutional blocks, which allows the network to model the long-term dependencies of the speech signal while maintaining a small model size. The proposed Conv-TasNet system significantly outperforms previous time-frequency masking methods in separating two- and three-speaker mixtures. Additionally, Conv-TasNet surpasses several ideal time-frequency magnitude masks in two-speaker speech separation as evaluated by both objective distortion measures and subjective quality assessment by human listeners. Finally, Conv-TasNet has a significantly smaller model size and a shorter minimum latency, making it a suitable solution for both offline and real-time speech separation applications.

We propose Wav2CLIP, a robust audio representation learning method by distilling from Contrastive Language-Image Pre-training (CLIP). We systematically evaluate Wav2CLIP on a variety of audio tasks including classification, retrieval, and generation, and show that Wav2CLIP can outperform several publicly available pre-trained audio representation algorithms. Wav2CLIP projects audio into a shared embedding space with images and text, which enables multimodal applications such as zero-shot classification, and cross-modal retrieval. Furthermore, Wav2CLIP needs just ~10% of the data to achieve competitive performance on downstream tasks compared with fully supervised models, and is more efficient to pre-train than competing methods as it does not require learning a visual model in concert with an auditory model. Finally, we demonstrate image generation from Wav2CLIP as qualitative assessment of the shared embedding space. Our code and model weights are open sourced and made available for further applications.

Voice conversion refers to transferring speaker identity with well-preserved content. Better disentanglement of speech representations leads to better voice conversion. Recent studies have found that phonetic information from input audio has the potential ability to well represent content. Besides, the speaker-style modeling with pre-trained models making the process more complex. To tackle these issues, we introduce a new method named "CTVC" which utilizes disentangled speech representations with contrastive learning and time-invariant retrieval. Specifically, a similarity-based compression module is used to facilitate a more intimate connection between the frame-level hidden features and linguistic information at phoneme-level. Additionally, a time-invariant retrieval is proposed for timbre extraction based on multiple segmentations and mutual information. Experimental results demonstrate that "CTVC" outperforms previous studies and improves the sound quality and similarity of converted results.

Connectionist Temporal Classification (CTC) is a widely used criterion for training supervised sequence-to-sequence (seq2seq) models. It enables learning the relations between input and output sequences, termed alignments, by marginalizing over perfect alignments (that yield the ground truth), at the expense of imperfect alignments. This binary differentiation of perfect and imperfect alignments falls short of capturing other essential alignment properties that hold significance in other real-world applications. Here we propose Align With Purpose, a general Plug-and-Play framework for enhancing a desired property in models trained with the CTC criterion. We do that by complementing the CTC with an additional loss term that prioritizes alignments according to a desired property. Our method does not require any intervention in the CTC loss function, enables easy optimization of a variety of properties, and allows differentiation between both perfect and imperfect alignments. We apply our framework in the domain of Automatic Speech Recognition (ASR) and show its generality in terms of property selection, architectural choice, and scale of training dataset (up to 280,000 hours). To demonstrate the effectiveness of our framework, we apply it to two unrelated properties: emission time and word error rate (WER). For the former, we report an improvement of up to 570ms in latency optimization with a minor reduction in WER, and for the latter, we report a relative improvement of 4.5% WER over the baseline models. To the best of our knowledge, these applications have never been demonstrated to work on a scale of data as large as ours. Notably, our method can be implemented using only a few lines of code, and can be extended to other alignment-free loss functions and to domains other than ASR.

Transformers have revolutionized deep learning across various tasks, including audio representation learning, due to their powerful modeling capabilities. However, they often suffer from quadratic complexity in both GPU memory usage and computational inference time, affecting their efficiency. Recently, state space models (SSMs) like Mamba have emerged as a promising alternative, offering a more efficient approach by avoiding these complexities. Given these advantages, we explore the potential of SSM-based models in audio tasks. In this paper, we introduce Self-Supervised Audio Mamba (SSAMBA), the first self-supervised, attention-free, and SSM-based model for audio representation learning. SSAMBA leverages the bidirectional Mamba to capture complex audio patterns effectively. We incorporate a self-supervised pretraining framework that optimizes both discriminative and generative objectives, enabling the model to learn robust audio representations from large-scale, unlabeled datasets. We evaluated SSAMBA on various tasks such as audio classification, keyword spotting, and speaker identification. Our results demonstrate that SSAMBA outperforms the Self-Supervised Audio Spectrogram Transformer (SSAST) in most tasks. Notably, SSAMBA is approximately 92.7% faster in batch inference speed and 95.4% more memory-efficient than SSAST for the tiny model size with an input token size of 22k. These efficiency gains, combined with superior performance, underscore the effectiveness of SSAMBA's architectural innovation, making it a compelling choice for a wide range of audio processing applications.

We introduce a new collection of spoken English audio suitable for training speech recognition systems under limited or no supervision. It is derived from open-source audio books from the LibriVox project. It contains over 60K hours of audio, which is, to our knowledge, the largest freely-available corpus of speech. The audio has been segmented using voice activity detection and is tagged with SNR, speaker ID and genre descriptions. Additionally, we provide baseline systems and evaluation metrics working under three settings: (1) the zero resource/unsupervised setting (ABX), (2) the semi-supervised setting (PER, CER) and (3) the distant supervision setting (WER). Settings (2) and (3) use limited textual resources (10 minutes to 10 hours) aligned with the speech. Setting (3) uses large amounts of unaligned text. They are evaluated on the standard LibriSpeech dev and test sets for comparison with the supervised state-of-the-art.

Modeling the errors of a speech recognizer can help simulate errorful recognized speech data from plain text, which has proven useful for tasks like discriminative language modeling, improving robustness of NLP systems, where limited or even no audio data is available at train time. Previous work typically considered replicating behavior of GMM-HMM based systems, but the behavior of more modern posterior-based neural network acoustic models is not the same and requires adjustments to the error prediction model. In this work, we extend a prior phonetic confusion based model for predicting speech recognition errors in two ways: first, we introduce a sampling-based paradigm that better simulates the behavior of a posterior-based acoustic model. Second, we investigate replacing the confusion matrix with a sequence-to-sequence model in order to introduce context dependency into the prediction. We evaluate the error predictors in two ways: first by predicting the errors made by a Switchboard ASR system on unseen data (Fisher), and then using that same predictor to estimate the behavior of an unrelated cloud-based ASR system on a novel task. Sampling greatly improves predictive accuracy within a 100-guess paradigm, while the sequence model performs similarly to the confusion matrix.

We introduce a sophisticated multi-speaker speech data simulator, specifically engineered to generate multi-speaker speech recordings. A notable feature of this simulator is its capacity to modulate the distribution of silence and overlap via the adjustment of statistical parameters. This capability offers a tailored training environment for developing neural models suited for speaker diarization and voice activity detection. The acquisition of substantial datasets for speaker diarization often presents a significant challenge, particularly in multi-speaker scenarios. Furthermore, the precise time stamp annotation of speech data is a critical factor for training both speaker diarization and voice activity detection. Our proposed multi-speaker simulator tackles these problems by generating large-scale audio mixtures that maintain statistical properties closely aligned with the input parameters. We demonstrate that the proposed multi-speaker simulator generates audio mixtures with statistical properties that closely align with the input parameters derived from real-world statistics. Additionally, we present the effectiveness of speaker diarization and voice activity detection models, which have been trained exclusively on the generated simulated datasets.

We present a fast and high-quality codec language model for parallel audio generation. While SoundStorm, a state-of-the-art parallel audio generation model, accelerates inference speed compared to autoregressive models, it still suffers from slow inference due to iterative sampling. To resolve this problem, we propose Group-Masked Language Modeling~(G-MLM) and Group Iterative Parallel Decoding~(G-IPD) for efficient parallel audio generation. Both the training and sampling schemes enable the model to synthesize high-quality audio with a small number of iterations by effectively modeling the group-wise conditional dependencies. In addition, our model employs a cross-attention-based architecture to capture the speaker style of the prompt voice and improves computational efficiency. Experimental results demonstrate that our proposed model outperforms the baselines in prompt-based audio generation.

Large-scale pre-trained image-text models demonstrate remarkable versatility across diverse tasks, benefiting from their robust representational capabilities and effective multimodal alignment. We extend the application of these models, specifically CLIP, to the domain of sound source localization. Unlike conventional approaches, we employ the pre-trained CLIP model without explicit text input, relying solely on the audio-visual correspondence. To this end, we introduce a framework that translates audio signals into tokens compatible with CLIP's text encoder, yielding audio-driven embeddings. By directly using these embeddings, our method generates audio-grounded masks for the provided audio, extracts audio-grounded image features from the highlighted regions, and aligns them with the audio-driven embeddings using the audio-visual correspondence objective. Our findings suggest that utilizing pre-trained image-text models enable our model to generate more complete and compact localization maps for the sounding objects. Extensive experiments show that our method outperforms state-of-the-art approaches by a significant margin.

Recently, instruction-following audio-language models have received broad attention for human-audio interaction. However, the absence of benchmarks capable of evaluating audio-centric interaction capabilities has impeded advancements in this field. Previous models primarily focus on assessing different fundamental tasks, such as Automatic Speech Recognition (ASR), and lack an assessment of the open-ended generative capabilities centered around audio. Thus, it is challenging to track the progression in the Large Audio-Language Models (LALMs) domain and to provide guidance for future improvement. In this paper, we introduce AIR-Bench (Audio InstRuction Benchmark), the first benchmark designed to evaluate the ability of LALMs to understand various types of audio signals (including human speech, natural sounds, and music), and furthermore, to interact with humans in the textual format. AIR-Bench encompasses two dimensions: foundation and chat benchmarks. The former consists of 19 tasks with approximately 19k single-choice questions, intending to inspect the basic single-task ability of LALMs. The latter one contains 2k instances of open-ended question-and-answer data, directly assessing the comprehension of the model on complex audio and its capacity to follow instructions. Both benchmarks require the model to generate hypotheses directly. We design a unified framework that leverages advanced language models, such as GPT-4, to evaluate the scores of generated hypotheses given the meta-information of the audio. Experimental results demonstrate a high level of consistency between GPT-4-based evaluation and human evaluation. By revealing the limitations of existing LALMs through evaluation results, AIR-Bench can provide insights into the direction of future research.

Self-supervised learning (SSL) achieves great success in speech recognition, while limited exploration has been attempted for other speech processing tasks. As speech signal contains multi-faceted information including speaker identity, paralinguistics, spoken content, etc., learning universal representations for all speech tasks is challenging. To tackle the problem, we propose a new pre-trained model, WavLM, to solve full-stack downstream speech tasks. WavLM jointly learns masked speech prediction and denoising in pre-training. By this means, WavLM does not only keep the speech content modeling capability by the masked speech prediction, but also improves the potential to non-ASR tasks by the speech denoising. In addition, WavLM employs gated relative position bias for the Transformer structure to better capture the sequence ordering of input speech. We also scale up the training dataset from 60k hours to 94k hours. WavLM Large achieves state-of-the-art performance on the SUPERB benchmark, and brings significant improvements for various speech processing tasks on their representative benchmarks. The code and pre-trained models are available at https://aka.ms/wavlm.

Augmenting large language models (LLMs) to understand audio -- including non-speech sounds and non-verbal speech -- is critically important for diverse real-world applications of LLMs. In this paper, we propose Audio Flamingo, a novel audio language model with 1) strong audio understanding abilities, 2) the ability to quickly adapt to unseen tasks via in-context learning and retrieval, and 3) strong multi-turn dialogue abilities. We introduce a series of training techniques, architecture design, and data strategies to enhance our model with these abilities. Extensive evaluations across various audio understanding tasks confirm the efficacy of our method, setting new state-of-the-art benchmarks.

Neural Transducer and connectionist temporal classification (CTC) are popular end-to-end automatic speech recognition systems. Due to their frame-synchronous design, blank symbols are introduced to address the length mismatch between acoustic frames and output tokens, which might bring redundant computation. Previous studies managed to accelerate the training and inference of neural Transducers by discarding frames based on the blank symbols predicted by a co-trained CTC. However, there is no guarantee that the co-trained CTC can maximize the ratio of blank symbols. This paper proposes two novel regularization methods to explicitly encourage more blanks by constraining the self-loop of non-blank symbols in the CTC. It is interesting to find that the frame reduction ratio of the neural Transducer can approach the theoretical boundary. Experiments on LibriSpeech corpus show that our proposed method accelerates the inference of neural Transducer by 4 times without sacrificing performance. Our work is open-sourced and publicly available https://github.com/k2-fsa/icefall.

Recurrent Neural Networks (RNNs) have long been the dominant architecture in sequence-to-sequence learning. RNNs, however, are inherently sequential models that do not allow parallelization of their computations. Transformers are emerging as a natural alternative to standard RNNs, replacing recurrent computations with a multi-head attention mechanism. In this paper, we propose the SepFormer, a novel RNN-free Transformer-based neural network for speech separation. The SepFormer learns short and long-term dependencies with a multi-scale approach that employs transformers. The proposed model achieves state-of-the-art (SOTA) performance on the standard WSJ0-2/3mix datasets. It reaches an SI-SNRi of 22.3 dB on WSJ0-2mix and an SI-SNRi of 19.5 dB on WSJ0-3mix. The SepFormer inherits the parallelization advantages of Transformers and achieves a competitive performance even when downsampling the encoded representation by a factor of 8. It is thus significantly faster and it is less memory-demanding than the latest speech separation systems with comparable performance.

We introduce a novel segmental-attention model for automatic speech recognition. We restrict the decoder attention to segments to avoid quadratic runtime of global attention, better generalize to long sequences, and eventually enable streaming. We directly compare global-attention and different segmental-attention modeling variants. We develop and compare two separate time-synchronous decoders, one specifically taking the segmental nature into account, yielding further improvements. Using time-synchronous decoding for segmental models is novel and a step towards streaming applications. Our experiments show the importance of a length model to predict the segment boundaries. The final best segmental-attention model using segmental decoding performs better than global-attention, in contrast to other monotonic attention approaches in the literature. Further, we observe that the segmental model generalizes much better to long sequences of up to several minutes.

Multitrack music transcription aims to transcribe a music audio input into the musical notes of multiple instruments simultaneously. It is a very challenging task that typically requires a more complex model to achieve satisfactory result. In addition, prior works mostly focus on transcriptions of regular instruments, however, neglecting vocals, which are usually the most important signal source if present in a piece of music. In this paper, we propose a novel deep neural network architecture, Perceiver TF, to model the time-frequency representation of audio input for multitrack transcription. Perceiver TF augments the Perceiver architecture by introducing a hierarchical expansion with an additional Transformer layer to model temporal coherence. Accordingly, our model inherits the benefits of Perceiver that posses better scalability, allowing it to well handle transcriptions of many instruments in a single model. In experiments, we train a Perceiver TF to model 12 instrument classes as well as vocal in a multi-task learning manner. Our result demonstrates that the proposed system outperforms the state-of-the-art counterparts (e.g., MT3 and SpecTNT) on various public datasets.

Recent advances in generative models that iteratively synthesize audio clips sparked great success to text-to-audio synthesis (TTA), but with the cost of slow synthesis speed and heavy computation. Although there have been attempts to accelerate the iterative procedure, high-quality TTA systems remain inefficient due to hundreds of iterations required in the inference phase and large amount of model parameters. To address the challenges, we propose SpecMaskGIT, a light-weighted, efficient yet effective TTA model based on the masked generative modeling of spectrograms. First, SpecMaskGIT synthesizes a realistic 10s audio clip by less than 16 iterations, an order-of-magnitude less than previous iterative TTA methods.As a discrete model, SpecMaskGIT outperforms larger VQ-Diffusion and auto-regressive models in the TTA benchmark, while being real-time with only 4 CPU cores or even 30x faster with a GPU. Next, built upon a latent space of Mel-spectrogram, SpecMaskGIT has a wider range of applications (e.g., the zero-shot bandwidth extension) than similar methods built on the latent wave domain. Moreover, we interpret SpecMaskGIT as a generative extension to previous discriminative audio masked Transformers, and shed light on its audio representation learning potential. We hope our work inspires the exploration of masked audio modeling toward further diverse scenarios.

The auditory system plays a substantial role in shaping the overall human perceptual experience. While prevailing large language models (LLMs) and visual language models (VLMs) have shown their promise in solving a wide variety of vision and language understanding tasks, only a few of them can be generalised to the audio domain without compromising their domain-specific capacity. In this work, we introduce Acoustic Prompt Turning (APT), a new adapter extending LLMs and VLMs to the audio domain by soft prompting only. Specifically, APT applies an instruction-aware audio aligner to generate soft prompts, conditioned on both input text and sounds, as language model inputs. To mitigate the data scarcity in the audio domain, a multi-task learning strategy is proposed by formulating diverse audio tasks in a sequence-to-sequence manner. Moreover, we improve the framework of audio language model by using interleaved audio-text embeddings as the input sequence. This improved framework imposes zero constraints on the input format and thus is capable of tackling more understanding tasks, such as few-shot audio classification and audio reasoning. To further evaluate the reasoning ability of audio networks, we propose natural language audio reasoning (NLAR), a new task that analyses across two audio clips by comparison and summarization. Experiments show that APT-enhanced LLMs (namely APT-LLMs) achieve competitive results compared to the expert models (i.e., the networks trained on the targeted datasets) across various tasks. We finally demonstrate the APT's ability in extending frozen VLMs to the audio domain without finetuning, achieving promising results in the audio-visual question and answering task. Our code and model weights are released at https://github.com/JinhuaLiang/APT.

Deep neural networks are a promising tool for Audio Event Classification. In contrast to other data like natural images, there are many sensible and non-obvious representations for audio data, which could serve as input to these models. Due to their black-box nature, the effect of different input representations has so far mostly been investigated by measuring classification performance. In this work, we leverage eXplainable AI (XAI), to understand the underlying classification strategies of models trained on different input representations. Specifically, we compare two model architectures with regard to relevant input features used for Audio Event Detection: one directly processes the signal as the raw waveform, and the other takes in its time-frequency spectrogram representation. We show how relevance heatmaps obtained via "Siren"{Layer-wise Relevance Propagation} uncover representation-dependent decision strategies. With these insights, we can make a well-informed decision about the best input representation in terms of robustness and representativity and confirm that the model's classification strategies align with human requirements.

Lyrics alignment gained considerable attention in recent years. State-of-the-art systems either re-use established speech recognition toolkits, or design end-to-end solutions involving a Connectionist Temporal Classification (CTC) loss. However, both approaches suffer from specific weaknesses: toolkits are known for their complexity, and CTC systems use a loss designed for transcription which can limit alignment accuracy. In this paper, we use instead a contrastive learning procedure that derives cross-modal embeddings linking the audio and text domains. This way, we obtain a novel system that is simple to train end-to-end, can make use of weakly annotated training data, jointly learns a powerful text model, and is tailored to alignment. The system is not only the first to yield an average absolute error below 0.2 seconds on the standard Jamendo dataset but it is also robust to other languages, even when trained on English data only. Finally, we release word-level alignments for the JamendoLyrics Multi-Lang dataset.

Recently, text-to-speech (TTS) models such as FastSpeech and ParaNet have been proposed to generate mel-spectrograms from text in parallel. Despite the advantage, the parallel TTS models cannot be trained without guidance from autoregressive TTS models as their external aligners. In this work, we propose Glow-TTS, a flow-based generative model for parallel TTS that does not require any external aligner. By combining the properties of flows and dynamic programming, the proposed model searches for the most probable monotonic alignment between text and the latent representation of speech on its own. We demonstrate that enforcing hard monotonic alignments enables robust TTS, which generalizes to long utterances, and employing generative flows enables fast, diverse, and controllable speech synthesis. Glow-TTS obtains an order-of-magnitude speed-up over the autoregressive model, Tacotron 2, at synthesis with comparable speech quality. We further show that our model can be easily extended to a multi-speaker setting.

Recent advancements in deep learning have led to widespread use of techniques for audio content generation, notably employing Denoising Diffusion Probabilistic Models (DDPM) across various tasks. Among these, Foley Sound Synthesis is of particular interest for its role in applications for the creation of multimedia content. Given the temporal-dependent nature of sound, it is crucial to design generative models that can effectively handle the sequential modeling of audio samples. Selective State Space Models (SSMs) have recently been proposed as a valid alternative to previously proposed techniques, demonstrating competitive performance with lower computational complexity. In this paper, we introduce MambaFoley, a diffusion-based model that, to the best of our knowledge, is the first to leverage the recently proposed SSM known as Mamba for the Foley sound generation task. To evaluate the effectiveness of the proposed method, we compare it with a state-of-the-art Foley sound generative model using both objective and subjective analyses.

We propose Guided-TTS 2, a diffusion-based generative model for high-quality adaptive TTS using untranscribed data. Guided-TTS 2 combines a speaker-conditional diffusion model with a speaker-dependent phoneme classifier for adaptive text-to-speech. We train the speaker-conditional diffusion model on large-scale untranscribed datasets for a classifier-free guidance method and further fine-tune the diffusion model on the reference speech of the target speaker for adaptation, which only takes 40 seconds. We demonstrate that Guided-TTS 2 shows comparable performance to high-quality single-speaker TTS baselines in terms of speech quality and speaker similarity with only a ten-second untranscribed data. We further show that Guided-TTS 2 outperforms adaptive TTS baselines on multi-speaker datasets even with a zero-shot adaptation setting. Guided-TTS 2 can adapt to a wide range of voices only using untranscribed speech, which enables adaptive TTS with the voice of non-human characters such as Gollum in "The Lord of the Rings".

Advancements in deep neural networks have allowed automatic speech recognition (ASR) systems to attain human parity on several publicly available clean speech datasets. However, even state-of-the-art ASR systems experience performance degradation when confronted with adverse conditions, as a well-trained acoustic model is sensitive to variations in the speech domain, e.g., background noise. Intuitively, humans address this issue by relying on their linguistic knowledge: the meaning of ambiguous spoken terms is usually inferred from contextual cues thereby reducing the dependency on the auditory system. Inspired by this observation, we introduce the first open-source benchmark to utilize external large language models (LLMs) for ASR error correction, where N-best decoding hypotheses provide informative elements for true transcription prediction. This approach is a paradigm shift from the traditional language model rescoring strategy that can only select one candidate hypothesis as the output transcription. The proposed benchmark contains a novel dataset, HyPoradise (HP), encompassing more than 334,000 pairs of N-best hypotheses and corresponding accurate transcriptions across prevalent speech domains. Given this dataset, we examine three types of error correction techniques based on LLMs with varying amounts of labeled hypotheses-transcription pairs, which gains a significant word error rate (WER) reduction. Experimental evidence demonstrates the proposed technique achieves a breakthrough by surpassing the upper bound of traditional re-ranking based methods. More surprisingly, LLM with reasonable prompt and its generative capability can even correct those tokens that are missing in N-best list. We make our results publicly accessible for reproducible pipelines with released pre-trained models, thus providing a new evaluation paradigm for ASR error correction with LLMs.

Although supervised deep learning has revolutionized speech and audio processing, it has necessitated the building of specialist models for individual tasks and application scenarios. It is likewise difficult to apply this to dialects and languages for which only limited labeled data is available. Self-supervised representation learning methods promise a single universal model that would benefit a wide variety of tasks and domains. Such methods have shown success in natural language processing and computer vision domains, achieving new levels of performance while reducing the number of labels required for many downstream scenarios. Speech representation learning is experiencing similar progress in three main categories: generative, contrastive, and predictive methods. Other approaches rely on multi-modal data for pre-training, mixing text or visual data streams with speech. Although self-supervised speech representation is still a nascent research area, it is closely related to acoustic word embedding and learning with zero lexical resources, both of which have seen active research for many years. This review presents approaches for self-supervised speech representation learning and their connection to other research areas. Since many current methods focus solely on automatic speech recognition as a downstream task, we review recent efforts on benchmarking learned representations to extend the application beyond speech recognition.

Although neural end-to-end text-to-speech models can synthesize highly natural speech, there is still room for improvements to its efficiency and naturalness. This paper proposes a non-autoregressive neural text-to-speech model augmented with a variational autoencoder-based residual encoder. This model, called Parallel Tacotron, is highly parallelizable during both training and inference, allowing efficient synthesis on modern parallel hardware. The use of the variational autoencoder relaxes the one-to-many mapping nature of the text-to-speech problem and improves naturalness. To further improve the naturalness, we use lightweight convolutions, which can efficiently capture local contexts, and introduce an iterative spectrogram loss inspired by iterative refinement. Experimental results show that Parallel Tacotron matches a strong autoregressive baseline in subjective evaluations with significantly decreased inference time.

We demonstrate that carefully adjusting the tokenizer of the Whisper speech recognition model significantly improves the precision of word-level timestamps when applying dynamic time warping to the decoder's cross-attention scores. We fine-tune the model to produce more verbatim speech transcriptions and employ several techniques to increase robustness against multiple speakers and background noise. These adjustments achieve state-of-the-art performance on benchmarks for verbatim speech transcription, word segmentation, and the timed detection of filler events, and can further mitigate transcription hallucinations. The code is available open https://github.com/nyrahealth/CrisperWhisper.

Most of existing audio fingerprinting systems have limitations to be used for high-specific audio retrieval at scale. In this work, we generate a low-dimensional representation from a short unit segment of audio, and couple this fingerprint with a fast maximum inner-product search. To this end, we present a contrastive learning framework that derives from the segment-level search objective. Each update in training uses a batch consisting of a set of pseudo labels, randomly selected original samples, and their augmented replicas. These replicas can simulate the degrading effects on original audio signals by applying small time offsets and various types of distortions, such as background noise and room/microphone impulse responses. In the segment-level search task, where the conventional audio fingerprinting systems used to fail, our system using 10x smaller storage has shown promising results. Our code and dataset are available at https://mimbres.github.io/neural-audio-fp/.

In the evolving field of Natural Language Processing, understanding the temporal context of text is increasingly crucial. This study investigates methods to incorporate temporal information during pre-training, aiming to achieve effective time-aware language representation for improved performance on time-related tasks. In contrast to common pre-trained models like BERT, which rely on synchronic document collections such as BookCorpus and Wikipedia, our research introduces BiTimeBERT 2.0, a novel language model pre-trained on a temporal news article collection. BiTimeBERT 2.0 utilizes this temporal news collection, focusing on three innovative pre-training objectives: Time-Aware Masked Language Modeling (TAMLM), Document Dating (DD), and Time-Sensitive Entity Replacement (TSER). Each objective targets a unique aspect of temporal information. TAMLM is designed to enhance the understanding of temporal contexts and relations, DD integrates document timestamps as chronological markers, and TSER focuses on the temporal dynamics of "Person" entities, recognizing their inherent temporal significance. The experimental results consistently demonstrate that BiTimeBERT 2.0 outperforms models like BERT and other existing pre-trained models, achieving substantial gains across a variety of downstream NLP tasks and applications where time plays a pivotal role.

Diffusion models have demonstrated significant potential in speech synthesis tasks, including text-to-speech (TTS) and voice cloning. However, their iterative denoising processes are inefficient and hinder the application of end-to-end optimization with perceptual metrics. In this paper, we propose a novel method of distilling TTS diffusion models with direct end-to-end evaluation metric optimization, achieving state-of-the-art performance. By incorporating Connectionist Temporal Classification (CTC) loss and Speaker Verification (SV) loss, our approach optimizes perceptual evaluation metrics, leading to notable improvements in word error rate and speaker similarity. Our experiments show that DMDSpeech consistently surpasses prior state-of-the-art models in both naturalness and speaker similarity while being significantly faster. Moreover, our synthetic speech has a higher level of voice similarity to the prompt than the ground truth in both human evaluation and objective speaker similarity metric. This work highlights the potential of direct metric optimization in speech synthesis, allowing models to better align with human auditory preferences. The audio samples are available at https://dmdspeech.github.io/.

We present a multi-speaker Japanese audiobook text-to-speech (TTS) system that leverages multimodal context information of preceding acoustic context and bilateral textual context to improve the prosody of synthetic speech. Previous work either uses unilateral or single-modality context, which does not fully represent the context information. The proposed method uses an acoustic context encoder and a textual context encoder to aggregate context information and feeds it to the TTS model, which enables the model to predict context-dependent prosody. We conducted comprehensive objective and subjective evaluations on a multi-speaker Japanese audiobook dataset. Experimental results demonstrate that the proposed method significantly outperforms two previous works. Additionally, we present insights about the different choices of context - modalities, lateral information and length - for audiobook TTS that have never been discussed in the literature before.

Diffusion models have shown a great ability at bridging the performance gap between predictive and generative approaches for speech enhancement. We have shown that they may even outperform their predictive counterparts for non-additive corruption types or when they are evaluated on mismatched conditions. However, diffusion models suffer from a high computational burden, mainly as they require to run a neural network for each reverse diffusion step, whereas predictive approaches only require one pass. As diffusion models are generative approaches they may also produce vocalizing and breathing artifacts in adverse conditions. In comparison, in such difficult scenarios, predictive models typically do not produce such artifacts but tend to distort the target speech instead, thereby degrading the speech quality. In this work, we present a stochastic regeneration approach where an estimate given by a predictive model is provided as a guide for further diffusion. We show that the proposed approach uses the predictive model to remove the vocalizing and breathing artifacts while producing very high quality samples thanks to the diffusion model, even in adverse conditions. We further show that this approach enables to use lighter sampling schemes with fewer diffusion steps without sacrificing quality, thus lifting the computational burden by an order of magnitude. Source code and audio examples are available online (https://uhh.de/inf-sp-storm).

We introduce MAGNeT, a masked generative sequence modeling method that operates directly over several streams of audio tokens. Unlike prior work, MAGNeT is comprised of a single-stage, non-autoregressive transformer. During training, we predict spans of masked tokens obtained from a masking scheduler, while during inference we gradually construct the output sequence using several decoding steps. To further enhance the quality of the generated audio, we introduce a novel rescoring method in which, we leverage an external pre-trained model to rescore and rank predictions from MAGNeT, which will be then used for later decoding steps. Lastly, we explore a hybrid version of MAGNeT, in which we fuse between autoregressive and non-autoregressive models to generate the first few seconds in an autoregressive manner while the rest of the sequence is being decoded in parallel. We demonstrate the efficiency of MAGNeT for the task of text-to-music and text-to-audio generation and conduct an extensive empirical evaluation, considering both objective metrics and human studies. The proposed approach is comparable to the evaluated baselines, while being significantly faster (x7 faster than the autoregressive baseline). Through ablation studies and analysis, we shed light on the importance of each of the components comprising MAGNeT, together with pointing to the trade-offs between autoregressive and non-autoregressive modeling, considering latency, throughput, and generation quality. Samples are available on our demo page https://pages.cs.huji.ac.il/adiyoss-lab/MAGNeT.

This paper introduces FALL-E, a foley synthesis system and its training/inference strategies. The FALL-E model employs a cascaded approach comprising low-resolution spectrogram generation, spectrogram super-resolution, and a vocoder. We trained every sound-related model from scratch using our extensive datasets, and utilized a pre-trained language model. We conditioned the model with dataset-specific texts, enabling it to learn sound quality and recording environment based on text input. Moreover, we leveraged external language models to improve text descriptions of our datasets and performed prompt engineering for quality, coherence, and diversity. FALL-E was evaluated by an objective measure as well as listening tests in the DCASE 2023 challenge Task 7. The submission achieved the second place on average, while achieving the best score for diversity, second place for audio quality, and third place for class fitness.

This paper introduces Embarrassingly Easy Text-to-Speech (E2 TTS), a fully non-autoregressive zero-shot text-to-speech system that offers human-level naturalness and state-of-the-art speaker similarity and intelligibility. In the E2 TTS framework, the text input is converted into a character sequence with filler tokens. The flow-matching-based mel spectrogram generator is then trained based on the audio infilling task. Unlike many previous works, it does not require additional components (e.g., duration model, grapheme-to-phoneme) or complex techniques (e.g., monotonic alignment search). Despite its simplicity, E2 TTS achieves state-of-the-art zero-shot TTS capabilities that are comparable to or surpass previous works, including Voicebox and NaturalSpeech 3. The simplicity of E2 TTS also allows for flexibility in the input representation. We propose several variants of E2 TTS to improve usability during inference. See https://aka.ms/e2tts/ for demo samples.

Following the rationale of end-to-end modeling, CTC, RNN-T or encoder-decoder-attention models for automatic speech recognition (ASR) use graphemes or grapheme-based subword units based on e.g. byte-pair encoding (BPE). The mapping from pronunciation to spelling is learned completely from data. In contrast to this, classical approaches to ASR employ secondary knowledge sources in the form of phoneme lists to define phonetic output labels and pronunciation lexica. In this work, we do a systematic comparison between grapheme- and phoneme-based output labels for an encoder-decoder-attention ASR model. We investigate the use of single phonemes as well as BPE-based phoneme groups as output labels of our model. To preserve a simplified and efficient decoder design, we also extend the phoneme set by auxiliary units to be able to distinguish homophones. Experiments performed on the Switchboard 300h and LibriSpeech benchmarks show that phoneme-based modeling is competitive to grapheme-based encoder-decoder-attention modeling.

Existing text-to-music models can produce high-quality audio with great diversity. However, textual prompts alone cannot precisely control temporal musical features such as chords and rhythm of the generated music. To address this challenge, we introduce MusiConGen, a temporally-conditioned Transformer-based text-to-music model that builds upon the pretrained MusicGen framework. Our innovation lies in an efficient finetuning mechanism, tailored for consumer-grade GPUs, that integrates automatically-extracted rhythm and chords as the condition signal. During inference, the condition can either be musical features extracted from a reference audio signal, or be user-defined symbolic chord sequence, BPM, and textual prompts. Our performance evaluation on two datasets -- one derived from extracted features and the other from user-created inputs -- demonstrates that MusiConGen can generate realistic backing track music that aligns well with the specified conditions. We open-source the code and model checkpoints, and provide audio examples online, https://musicongen.github.io/musicongen_demo/.

This paper introduces a novel Token-and-Duration Transducer (TDT) architecture for sequence-to-sequence tasks. TDT extends conventional RNN-Transducer architectures by jointly predicting both a token and its duration, i.e. the number of input frames covered by the emitted token. This is achieved by using a joint network with two outputs which are independently normalized to generate distributions over tokens and durations. During inference, TDT models can skip input frames guided by the predicted duration output, which makes them significantly faster than conventional Transducers which process the encoder output frame by frame. TDT models achieve both better accuracy and significantly faster inference than conventional Transducers on different sequence transduction tasks. TDT models for Speech Recognition achieve better accuracy and up to 2.82X faster inference than conventional Transducers. TDT models for Speech Translation achieve an absolute gain of over 1 BLEU on the MUST-C test compared with conventional Transducers, and its inference is 2.27X faster. In Speech Intent Classification and Slot Filling tasks, TDT models improve the intent accuracy by up to over 1% (absolute) over conventional Transducers, while running up to 1.28X faster. Our implementation of the TDT model will be open-sourced with the NeMo (https://github.com/NVIDIA/NeMo) toolkit.

Automated audio captioning aims at generating natural language descriptions for given audio clips, not only detecting and classifying sounds, but also summarizing the relationships between audio events. Recent research advances in audio captioning have introduced additional guidance to improve the accuracy of audio events in generated sentences. However, temporal relations between audio events have received little attention while revealing complex relations is a key component in summarizing audio content. Therefore, this paper aims to better capture temporal relationships in caption generation with sound event detection (SED), a task that locates events' timestamps. We investigate the best approach to integrate temporal information in a captioning model and propose a temporal tag system to transform the timestamps into comprehensible relations. Results evaluated by the proposed temporal metrics suggest that great improvement is achieved in terms of temporal relation generation.

Prior works have demonstrated zero-shot text-to-speech by using a generative language model on audio tokens obtained via a neural audio codec. It is still challenging, however, to adapt them to low-latency scenarios. In this paper, we present LiveSpeech - a fully autoregressive language model-based approach for zero-shot text-to-speech, enabling low-latency streaming of the output audio. To allow multiple token prediction within a single decoding step, we propose (1) using adaptive codebook loss weights that consider codebook contribution in each frame and focus on hard instances, and (2) grouping codebooks and processing groups in parallel. Experiments show our proposed models achieve competitive results to state-of-the-art baselines in terms of content accuracy, speaker similarity, audio quality, and inference speed while being suitable for low-latency streaming applications.

This paper presents the sound event localization and detection (SELD) task setup for the DCASE 2019 challenge. The goal of the SELD task is to detect the temporal activities of a known set of sound event classes, and further localize them in space when active. As part of the challenge, a synthesized dataset with each sound event associated with a spatial coordinate represented using azimuth and elevation angles is provided. These sound events are spatialized using real-life impulse responses collected at multiple spatial coordinates in five different rooms with varying dimensions and material properties. A baseline SELD method employing a convolutional recurrent neural network is used to generate benchmark scores for this reverberant dataset. The benchmark scores are obtained using the recommended cross-validation setup.

Large-scale multimodal generative modeling has created milestones in text-to-image and text-to-video generation. Its application to audio still lags behind for two main reasons: the lack of large-scale datasets with high-quality text-audio pairs, and the complexity of modeling long continuous audio data. In this work, we propose Make-An-Audio with a prompt-enhanced diffusion model that addresses these gaps by 1) introducing pseudo prompt enhancement with a distill-then-reprogram approach, it alleviates data scarcity with orders of magnitude concept compositions by using language-free audios; 2) leveraging spectrogram autoencoder to predict the self-supervised audio representation instead of waveforms. Together with robust contrastive language-audio pretraining (CLAP) representations, Make-An-Audio achieves state-of-the-art results in both objective and subjective benchmark evaluation. Moreover, we present its controllability and generalization for X-to-Audio with "No Modality Left Behind", for the first time unlocking the ability to generate high-definition, high-fidelity audios given a user-defined modality input. Audio samples are available at https://Text-to-Audio.github.io

We propose Diffusion Inference-Time T-Optimization (DITTO), a general-purpose frame-work for controlling pre-trained text-to-music diffusion models at inference-time via optimizing initial noise latents. Our method can be used to optimize through any differentiable feature matching loss to achieve a target (stylized) output and leverages gradient checkpointing for memory efficiency. We demonstrate a surprisingly wide-range of applications for music generation including inpainting, outpainting, and looping as well as intensity, melody, and musical structure control - all without ever fine-tuning the underlying model. When we compare our approach against related training, guidance, and optimization-based methods, we find DITTO achieves state-of-the-art performance on nearly all tasks, including outperforming comparable approaches on controllability, audio quality, and computational efficiency, thus opening the door for high-quality, flexible, training-free control of diffusion models. Sound examples can be found at https://DITTO-Music.github.io/web/.

This paper presents a way of doing large scale audio understanding without traditional state of the art neural architectures. Ever since the introduction of deep learning for understanding audio signals in the past decade, convolutional architectures have been able to achieve state of the art results surpassing traditional hand-crafted features. In the recent past, there has been a similar shift away from traditional convolutional and recurrent neural networks towards purely end-to-end Transformer architectures. We, in this work, explore an approach, based on Bag-of-Words model. Our approach does not have any convolutions, recurrence, attention, transformers or other approaches such as BERT. We utilize micro and macro level clustered vanilla embeddings, and use a MLP head for classification. We only use feed-forward encoder-decoder models to get the bottlenecks of spectral envelops, spectral patches and slices as well as multi-resolution spectra. A classification head (a feed-forward layer), similar to the approach in SimCLR is trained on a learned representation. Using simple codes learned on latent representations, we show how we surpass traditional convolutional neural network architectures, and come strikingly close to outperforming powerful Transformer architectures. This work hopefully would pave way for exciting advancements in the field of representation learning without massive, end-to-end neural architectures.

We propose PromptTTS++, a prompt-based text-to-speech (TTS) synthesis system that allows control over speaker identity using natural language descriptions. To control speaker identity within the prompt-based TTS framework, we introduce the concept of speaker prompt, which describes voice characteristics (e.g., gender-neutral, young, old, and muffled) designed to be approximately independent of speaking style. Since there is no large-scale dataset containing speaker prompts, we first construct a dataset based on the LibriTTS-R corpus with manually annotated speaker prompts. We then employ a diffusion-based acoustic model with mixture density networks to model diverse speaker factors in the training data. Unlike previous studies that rely on style prompts describing only a limited aspect of speaker individuality, such as pitch, speaking speed, and energy, our method utilizes an additional speaker prompt to effectively learn the mapping from natural language descriptions to the acoustic features of diverse speakers. Our subjective evaluation results show that the proposed method can better control speaker characteristics than the methods without the speaker prompt. Audio samples are available at https://reppy4620.github.io/demo.promptttspp/.

Using unsupervised learning to disentangle speech into content, rhythm, pitch, and timbre for voice conversion has become a hot research topic. Existing works generally take into account disentangling speech components through human-crafted bottleneck features which can not achieve sufficient information disentangling, while pitch and rhythm may still be mixed together. There is a risk of information overlap in the disentangling process which results in less speech naturalness. To overcome such limits, we propose a two-stage model to disentangle speech representations in a self-supervised manner without a human-crafted bottleneck design, which uses the Mutual Information (MI) with the designed upper bound estimator (IFUB) to separate overlapping information between speech components. Moreover, we design a Joint Text-Guided Consistent (TGC) module to guide the extraction of speech content and eliminate timbre leakage issues. Experiments show that our model can achieve a better performance than the baseline, regarding disentanglement effectiveness, speech naturalness, and similarity. Audio samples can be found at https://largeaudiomodel.com/eadvc.

Large language models (LLMs) have shown great promise for capturing contextual information in natural language processing tasks. We propose a novel approach to speaker diarization that incorporates the prowess of LLMs to exploit contextual cues in human dialogues. Our method builds upon an acoustic-based speaker diarization system by adding lexical information from an LLM in the inference stage. We model the multi-modal decoding process probabilistically and perform joint acoustic and lexical beam search to incorporate cues from both modalities: audio and text. Our experiments demonstrate that infusing lexical knowledge from the LLM into an acoustics-only diarization system improves overall speaker-attributed word error rate (SA-WER). The experimental results show that LLMs can provide complementary information to acoustic models for the speaker diarization task via proposed beam search decoding approach showing up to 39.8% relative delta-SA-WER improvement from the baseline system. Thus, we substantiate that the proposed technique is able to exploit contextual information that is inaccessible to acoustics-only systems which is represented by speaker embeddings. In addition, these findings point to the potential of using LLMs to improve speaker diarization and other speech processing tasks by capturing semantic and contextual cues.

We introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models, PaLM-2 [Anil et al., 2023] and AudioLM [Borsos et al., 2022], into a unified multimodal architecture that can process and generate text and speech with applications including speech recognition and speech-to-speech translation. AudioPaLM inherits the capability to preserve paralinguistic information such as speaker identity and intonation from AudioLM and the linguistic knowledge present only in text large language models such as PaLM-2. We demonstrate that initializing AudioPaLM with the weights of a text-only large language model improves speech processing, successfully leveraging the larger quantity of text training data used in pretraining to assist with the speech tasks. The resulting model significantly outperforms existing systems for speech translation tasks and has the ability to perform zero-shot speech-to-text translation for many languages for which input/target language combinations were not seen in training. AudioPaLM also demonstrates features of audio language models, such as transferring a voice across languages based on a short spoken prompt. We release examples of our method at https://google-research.github.io/seanet/audiopalm/examples

Text-to-audio (TTA) system has recently gained attention for its ability to synthesize general audio based on text descriptions. However, previous studies in TTA have limited generation quality with high computational costs. In this study, we propose AudioLDM, a TTA system that is built on a latent space to learn the continuous audio representations from contrastive language-audio pretraining (CLAP) latents. The pretrained CLAP models enable us to train LDMs with audio embedding while providing text embedding as a condition during sampling. By learning the latent representations of audio signals and their compositions without modeling the cross-modal relationship, AudioLDM is advantageous in both generation quality and computational efficiency. Trained on AudioCaps with a single GPU, AudioLDM achieves state-of-the-art TTA performance measured by both objective and subjective metrics (e.g., frechet distance). Moreover, AudioLDM is the first TTA system that enables various text-guided audio manipulations (e.g., style transfer) in a zero-shot fashion. Our implementation and demos are available at https://audioldm.github.io.