Luca Della Libera

FocalCodec: Low-Bitrate Speech Coding via Focal Modulation Networks

Large language models have revolutionized natural language processing through self-supervised pretraining on massive datasets. Inspired by t… (voir plus)his success, researchers have explored adapting these methods to speech by discretizing continuous audio into tokens using neural audio codecs. However, existing approaches face limitations, including high bitrates, the loss of either semantic or acoustic information, and the reliance on multi-codebook designs when trying to capture both, which increases architectural complexity for downstream tasks. To address these challenges, we introduce FocalCodec, an efficient low-bitrate codec based on focal modulation that utilizes a single binary codebook to compress speech between 0.16 and 0.65 kbps. FocalCodec delivers competitive performance in speech resynthesis and voice conversion at lower bitrates than the current state-of-the-art, while effectively handling multilingual speech and noisy environments. Evaluation on downstream tasks shows that FocalCodec successfully preserves sufficient semantic and acoustic information, while also being well-suited for generative modeling. Demo samples, code and checkpoints are available at https://lucadellalib.github.io/focalcodec-web/.

2025-02-06

ArXiv (prépublication)

FocalCodec: Low-Bitrate Speech Coding via Focal Modulation Networks

Large language models have revolutionized natural language processing through self-supervised pretraining on massive datasets. Inspired by t… (voir plus)his success, researchers have explored adapting these methods to speech by discretizing continuous audio into tokens using neural audio codecs. However, existing approaches face limitations, including high bitrates, the loss of either semantic or acoustic information, and the reliance on multi-codebook designs when trying to capture both, which increases architectural complexity for downstream tasks. To address these challenges, we introduce FocalCodec, an efficient low-bitrate codec based on focal modulation that utilizes a single binary codebook to compress speech between 0.16 and 0.65 kbps. FocalCodec delivers competitive performance in speech resynthesis and voice conversion at lower bitrates than the current state-of-the-art, while effectively handling multilingual speech and noisy environments. Evaluation on downstream tasks shows that FocalCodec successfully preserves sufficient semantic and acoustic information, while also being well-suited for generative modeling. Demo samples, code and checkpoints are available at https://lucadellalib.github.io/focalcodec-web/.

2025-02-06

ArXiv (prépublication)

Listenable Maps for Zero-Shot Audio Classifiers

Interpreting the decisions of deep learning models, including audio classifiers, is crucial for ensuring the transparency and trustworthines… (voir plus)s of this technology. In this paper, we introduce LMAC-ZS (Listenable Maps for Audio Classifiers in the Zero-Shot context), which, to the best of our knowledge, is the first decoder-based post-hoc interpretation method for explaining the decisions of zero-shot audio classifiers. The proposed method utilizes a novel loss function that maximizes the faithfulness to the original similarity between a given text-and-audio pair. We provide an extensive evaluation using the Contrastive Language-Audio Pretraining (CLAP) model to showcase that our interpreter remains faithful to the decisions in a zero-shot classification context. Moreover, we qualitatively show that our method produces meaningful explanations that correlate well with different text prompts.

2024-09-25

NeurIPS.cc/2024/Conference (poster)

openreview.net

Open-Source Conversational AI with SpeechBrain 1.0

Titouan Parcollet

Adel Moumen

Sylvain de Langen

Peter William VanHarn Plantinga

Yingzhi Wang

Davide Borra

Salah Zaiem

Zeyu Zhao

Shucong Zhang

Georgios Karakasidis

Sung-Lin Yeh

Pierre Champion

Aku Rouhe

Rudolf Braun … (voir 11 de plus)

Florian Mai

Juan Pablo Zuluaga

Seyed Mahed Mousavi

Andreas Nautsch

Xuechen Liu

Sangeet Sagar

Jarod Duret

Salima Mdhaffar

G. Laperriere

Renato De Mori

Yannick Estève

SpeechBrain is an open-source Conversational AI toolkit based on PyTorch, focused particularly on speech processing tasks such as speech rec… (voir plus)ognition, speech enhancement, speaker recognition, text-to-speech, and much more. It promotes transparency and replicability by releasing both the pre-trained models and the complete"recipes"of code and algorithms required for training them. This paper presents SpeechBrain 1.0, a significant milestone in the evolution of the toolkit, which now has over 200 recipes for speech, audio, and language processing tasks, and more than 100 models available on Hugging Face. SpeechBrain 1.0 introduces new technologies to support diverse learning modalities, Large Language Model (LLM) integration, and advanced decoding strategies, along with novel models, tasks, and modalities. It also includes a new benchmark repository, offering researchers a unified platform for evaluating models across diverse tasks.

2024-06-29

ArXiv (prépublication)

Open-Source Conversational AI with SpeechBrain 1.0

Titouan Parcollet

Adel Moumen

Sylvain de Langen

Peter William VanHarn Plantinga

Yingzhi Wang

Davide Borra

Salah Zaiem

Zeyu Zhao

Shucong Zhang

Georgios Karakasidis

Sung-Lin Yeh

Pierre Champion

Aku Rouhe

Rudolf Braun … (voir 11 de plus)

Florian Mai

Juan Pablo Zuluaga

Seyed Mahed Mousavi

Andreas Nautsch

Xuechen Liu

Sangeet Sagar

Jarod Duret

Salima Mdhaffar

G. Laperriere

Renato De Mori

Yannick Estève

SpeechBrain is an open-source Conversational AI toolkit based on PyTorch, focused particularly on speech processing tasks such as speech rec… (voir plus)ognition, speech enhancement, speaker recognition, text-to-speech, and much more. It promotes transparency and replicability by releasing both the pre-trained models and the complete"recipes"of code and algorithms required for training them. This paper presents SpeechBrain 1.0, a significant milestone in the evolution of the toolkit, which now has over 200 recipes for speech, audio, and language processing tasks, and more than 100 models available on Hugging Face. SpeechBrain 1.0 introduces new technologies to support diverse learning modalities, Large Language Model (LLM) integration, and advanced decoding strategies, along with novel models, tasks, and modalities. It also includes a new benchmark repository, offering researchers a unified platform for evaluating models across diverse tasks

2024-06-29

ArXiv (prépublication)

DASB -- Discrete Audio and Speech Benchmark

Jarod Duret

Discrete audio tokens have recently gained considerable attention for their potential to connect audio and language processing, enabling the… (voir plus) creation of modern multimodal large language models. Ideal audio tokens must effectively preserve phonetic and semantic content along with paralinguistic information, speaker identity, and other details. While several types of audio tokens have been recently proposed, identifying the optimal tokenizer for various tasks is challenging due to the inconsistent evaluation settings in existing studies. To address this gap, we release the Discrete Audio and Speech Benchmark (DASB), a comprehensive leaderboard for benchmarking discrete audio tokens across a wide range of discriminative tasks, including speech recognition, speaker identification and verification, emotion recognition, keyword spotting, and intent classification, as well as generative tasks such as speech enhancement, separation, and text-to-speech. Our results show that, on average, semantic tokens outperform compression tokens across most discriminative and generative tasks. However, the performance gap between semantic tokens and standard continuous representations remains substantial, highlighting the need for further research in this field.

2024-06-20

ArXiv (prépublication)

openreview.net

How Should We Extract Discrete Audio Tokens from Self-Supervised Models?

Pooneh Mousavi

Jarod Duret

Salah Zaiem

Discrete audio tokens have recently gained attention for their potential to bridge the gap between audio and language processing. Ideal audi… (voir plus)o tokens must preserve content, paralinguistic elements, speaker identity, and many other audio details. Current audio tokenization methods fall into two categories: Semantic tokens, acquired through quantization of Self-Supervised Learning (SSL) models, and Neural compression-based tokens (codecs). Although previous studies have benchmarked codec models to identify optimal configurations, the ideal setup for quantizing pretrained SSL models remains unclear. This paper explores the optimal configuration of semantic tokens across discriminative and generative tasks. We propose a scalable solution to train a universal vocoder across multiple SSL layers. Furthermore, an attention mechanism is employed to identify task-specific influential layers, enhancing the adaptability and performance of semantic tokens in diverse audio applications.

2024-06-15

ArXiv (prépublication)

Focal Modulation Networks for Interpretable Sound Classification

The increasing success of deep neural networks has raised concerns about their inherent black-box nature, posing challenges related to inter… (voir plus)pretability and trust. While there has been extensive exploration of interpretation techniques in vision and language, interpretability in the audio domain has received limited attention, primarily focusing on post-hoc explanations. This paper addresses the problem of interpretability by-design in the audio domain by utilizing the recently proposed attention-free focal modulation networks (FocalNets). We apply FocalNets to the task of environmental sound classification for the first time and evaluate their interpretability properties on the popular ESC-50 dataset. Our method outperforms a similarly sized vision transformer both in terms of accuracy and interpretability. Furthermore, it is competitive against PIQ, a method specifically designed for post-hoc interpretation in the audio domain.

2024-04-14

2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW) (publié)

Resource-Efficient Separation Transformer

Samuele Cornell

Frédéric Lepoutre

François Grondin

Transformers have recently achieved state-of-the-art performance in speech separation. These models, however, are computationally demanding … (voir plus)and require a lot of learnable parameters. This paper explores Transformer-based speech separation with a reduced computational cost. Our main contribution is the development of the Resource-Efficient Separation Transformer (RE-SepFormer), a self-attention-based architecture that reduces the computational burden in two ways. First, it uses non-overlapping blocks in the latent space. Second, it operates on compact latent summaries calculated from each chunk. The RE-SepFormer reaches a competitive performance on the popular WSJ0-2Mix and WHAM! datasets in both causal and non-causal settings. Remarkably, it scales significantly better than the previous Transformer-based architectures in terms of memory and inference time, making it more suitable for processing long mixtures.

2024-04-14

ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (publié)

Bayesian Deep Learning for Remaining Useful Life Estimation via Stein Variational Gradient Descent

Jacopo Andreoli

Davide Dalle Pezze

Gian Antonio Susto

A crucial task in predictive maintenance is estimating the remaining useful life of physical systems. In the last decade, deep learning has … (voir plus)improved considerably upon traditional model-based and statistical approaches in terms of predictive performance. However, in order to optimally plan maintenance operations, it is also important to quantify the uncertainty inherent to the predictions. This issue can be addressed by turning standard frequentist neural networks into Bayesian neural networks, which are naturally capable of providing confidence intervals around the estimates. Several methods exist for training those models. Researchers have focused mostly on parametric variational inference and sampling-based techniques, which notoriously suffer from limited approximation power and large computational burden, respectively. In this work, we use Stein variational gradient descent, a recently proposed algorithm for approximating intractable distributions that overcomes the drawbacks of the aforementioned techniques. In particular, we show through experimental studies on simulated run-to-failure turbofan engine degradation data that Bayesian deep learning models trained via Stein variational gradient descent consistently outperform with respect to convergence speed and predictive performance both the same models trained via parametric variational inference and their frequentist counterparts trained via backpropagation. Furthermore, we propose a method to enhance performance based on the uncertainty information provided by the Bayesian models. We release the source code at https://github.com/lucadellalib/bdl-rul-svgd.

2024-02-02

ArXiv (prépublication)

Bayesian Deep Learning for Remaining Useful Life Estimation via Stein Variational Gradient Descent

Jacopo Andreoli

Davide Dalle Pezze

Gian Antonio Susto

A crucial task in predictive maintenance is estimating the remaining useful life of physical systems. In the last decade, deep learning has … (voir plus)improved considerably upon traditional model-based and statistical approaches in terms of predictive performance. However, in order to optimally plan maintenance operations, it is also important to quantify the uncertainty inherent to the predictions. This issue can be addressed by turning standard frequentist neural networks into Bayesian neural networks, which are naturally capable of providing confidence intervals around the estimates. Several methods exist for training those models. Researchers have focused mostly on parametric variational inference and sampling-based techniques, which notoriously suffer from limited approximation power and large computational burden, respectively. In this work, we use Stein variational gradient descent, a recently proposed algorithm for approximating intractable distributions that overcomes the drawbacks of the aforementioned techniques. In particular, we show through experimental studies on simulated run-to-failure turbofan engine degradation data that Bayesian deep learning models trained via Stein variational gradient descent consistently outperform with respect to convergence speed and predictive performance both the same models trained via parametric variational inference and their frequentist counterparts trained via backpropagation. Furthermore, we propose a method to enhance performance based on the uncertainty information provided by the Bayesian models. We release the source code at https://github.com/lucadellalib/bdl-rul-svgd.

2024-02-02

ArXiv (prépublication)