Pooneh Mousavi

Investigating Faithfulness in Large Audio Language Models

Lovenya Jain

Faithfulness measures whether chain-of-thought (CoT) representations accurately reflect a model's decision process and can be used as reliab… (voir plus)le explanations. Prior work has shown that CoTs from text-based LLMs are often unfaithful. This question has not been explored for large audio-language models (LALMs), where faithfulness is critical for safety-sensitive applications. Reasoning in LALMs is also more challenging, as models must first extract relevant clues from audio before reasoning over them. In this paper, we investigate the faithfulness of CoTs produced by several LALMs by applying targeted interventions, including paraphrasing, filler token injection, early answering, and introducing mistakes, on two challenging reasoning datasets: SAKURA and MMAR. After going through the aforementioned interventions across several datasets and tasks, our experiments suggest that, LALMs generally produce CoTs that appear to be faithful to their underlying decision processes.

2025-09-26

ArXiv (prépublication)

Discrete Audio Tokens: More Than a Survey!

Gallil Maimon

Adel Moumen

Darius Petermann

Jiatong Shi

Haibin Wu

Haici Yang

Anastasia Kuznetsova

Ricard Marxer

Bhuvana Ramabhadran

Benjamin Elizalde

Loren Lugosch

Jinyu Li

Phil Woodland

Minje Kim

Hung-yi Lee

Shinji Watanabe

Yossi Adi … (voir 1 de plus)

Discrete audio tokens are compact representations that aim to preserve perceptual quality, phonetic content, and speaker characteristics whi… (voir plus)le enabling efficient storage and inference, as well as competitive performance across diverse downstream tasks. They provide a practical alternative to continuous features, enabling the integration of speech and audio into modern large language models (LLMs). As interest in token-based audio processing grows, various tokenization methods have emerged, and several surveys have reviewed the latest progress in the field. However, existing studies often focus on specific domains or tasks and lack a unified comparison across various benchmarks. This paper presents a systematic review and benchmark of discrete audio tokenizers, covering three domains: speech, music, and general audio. We propose a taxonomy of tokenization approaches based on encoder-decoder, quantization techniques, training paradigm, streamability, and application domains. We evaluate tokenizers on multiple benchmarks for reconstruction, downstream performance, and acoustic language modeling, and analyze trade-offs through controlled ablation studies. Our findings highlight key limitations, practical considerations, and open challenges, providing insight and guidance for future research in this rapidly evolving area. For more information, including our main results and tokenizer database, please refer to our website: https://poonehmousavi.github.io/dates-website/.

2025-06-12

ArXiv (prépublication)

Discrete Audio Tokens: More Than a Survey!

Gallil Maimon

Adel Moumen

Darius Petermann

Jiatong Shi

Haibin Wu

Haici Yang

Anastasia Kuznetsova

Ricard Marxer

Bhuvana Ramabhadran

Benjamin Elizalde

Loren Lugosch

Jinyu Li

Phil Woodland

Minje Kim

Hung-yi Lee

Shinji Watanabe

Yossi Adi … (voir 1 de plus)

Discrete audio tokens are compact representations that aim to preserve perceptual quality, phonetic content, and speaker characteristics whi… (voir plus)le enabling efficient storage and inference, as well as competitive performance across diverse downstream tasks.They provide a practical alternative to continuous features, enabling the integration of speech and audio into modern large language models (LLMs). As interest in token-based audio processing grows, various tokenization methods have emerged, and several surveys have reviewed the latest progress in the field. However, existing studies often focus on specific domains or tasks and lack a unified comparison across various benchmarks. This paper presents a systematic review and benchmark of discrete audio tokenizers, covering three domains: speech, music, and general audio. We propose a taxonomy of tokenization approaches based on encoder-decoder, quantization techniques, training paradigm, streamability, and application domains. We evaluate tokenizers on multiple benchmarks for reconstruction, downstream performance, and acoustic language modeling, and analyze trade-offs through controlled ablation studies. Our findings highlight key limitations, practical considerations, and open challenges, providing insight and guidance for future research in this rapidly evolving area. For more information, including our main results and tokenizer database, please refer to our website: https://poonehmousavi.github.io/dates-website/.

2025-06-12

ArXiv (prépublication)

LiSTEN: Learning Soft Token Embeddings for Neural Audio LLMs

Foundation models based on large language models (LLMs) have shown great success in handling various tasks and modalities. However, adapting… (voir plus) these models for general-purpose audio-language tasks is challenging due to differences in acoustic environments and task variations. In this work, we introduce LiSTEN Learning Soft Token Embeddings for Neural Audio LLMs), a framework for adapting LLMs to speech and audio tasks. LiSTEN uses a dynamic prompt selection strategy with learnable key-value pairs, allowing the model to balance general and task-specific knowledge while avoiding overfitting in a multitask setting. Our approach reduces dependence on large-scale ASR or captioning datasets, achieves competitive performance with fewer trainable parameters, and simplifies training by using a single-stage process. Additionally, LiSTEN enhances interpretability by analyzing the diversity and overlap of selected prompts across different tasks.

2025-05-24

ArXiv (prépublication)

ALAS: Measuring Latent Speech-Text Alignment For Spoken Language Understanding In Multimodal LLMs

Yingzhi Wang

2025-05-01

arXiv (publié)

LiSTEN: Learning Soft Token Embeddings for Neural Audio LLMs

Foundation models based on large language models (LLMs) have shown great success in handling various tasks and modalities. However, adapting… (voir plus) these models for general-purpose audio-language tasks is challenging due to differences in acoustic environments and task variations. In this work, we introduce LiSTEN Learning Soft Token Embeddings for Neural Audio LLMs), a framework for adapting LLMs to speech and audio tasks. LiSTEN uses a dynamic prompt selection strategy with learnable key-value pairs, allowing the model to balance general and task-specific knowledge while avoiding overfitting in a multitask setting. Our approach reduces dependence on large-scale ASR or captioning datasets, achieves competitive performance with fewer trainable parameters, and simplifies training by using a single-stage process. Additionally, LiSTEN enhances interpretability by analyzing the diversity and overlap of selected prompts across different tasks.

2025-05-01

arXiv (publié)

Discrete Audio Tokens: More Than a Survey!

Gallil Maimon

Adel Moumen

Darius Petermann

Jiatong Shi

Haibin Wu

Haici Yang

Anastasia Kuznetsova

Ricard Marxer

Bhuvana Ramabhadran

Benjamin Elizalde

Loren Lugosch

Jinyu Li

Phil Woodland

Minje Kim

Hung-yi Lee

Shinji Watanabe

Yossi Adi … (voir 1 de plus)

Discrete audio tokens are compact representations that aim to preserve perceptual quality, phonetic content, and speaker characteristics whi… (voir plus)le enabling efficient storage and inference, as well as competitive performance across diverse downstream tasks. They provide a practical alternative to continuous features, enabling the integration of speech and audio into modern large language models (LLMs). As interest in token-based audio processing grows, various tokenization methods have emerged, and several surveys have reviewed the latest progress in the field. However, existing studies often focus on specific domains or tasks and lack a unified comparison across various benchmarks. This paper presents a systematic review and benchmark of discrete audio tokenizers, covering three domains: speech, music, and general audio. We propose a taxonomy of tokenization approaches based on encoder-decoder, quantization techniques, training paradigm, streamability, and application domains. We evaluate tokenizers on multiple benchmarks for reconstruction, downstream performance, and acoustic language modeling, and analyze trade-offs through controlled ablation studies. Our findings highlight key limitations, practical considerations, and open challenges, providing insight and guidance for future research in this rapidly evolving area. For more information, including our main results and tokenizer database, please refer to our website: https://poonehmousavi.github.io/dates-website/.

2025-01-01

Trans. Mach. Learn. Res. (publié)

openreview.net

What Are They Doing? Joint Audio-Speech Co-Reasoning

Yingzhi Wang

2024-09-22

ArXiv (prépublication)

What Are They Doing? Joint Audio-Speech Co-Reasoning

Yingzhi Wang

In audio and speech processing, tasks usually focus on either the audio or speech modality, even when both sounds and human speech are prese… (voir plus)nt in the same audio clip. Recent Auditory Large Language Models (ALLMs) have made it possible to process audio and speech simultaneously within a single model, leading to further considerations of joint audio-speech tasks. In this paper, we establish a novel benchmark to investigate how well ALLMs can perform joint audio-speech processing. Specifically, we introduce Joint Audio-Speech Co-Reasoning (JASCO), a novel task that unifies audio and speech processing, strictly requiring co-reasoning across both modalities. We also release a scene-reasoning dataset called"What Are They Doing". Additionally, we provide deeper insights into the models' behaviors by analyzing their dependence on each modality.

2024-09-22

ArXiv (prépublication)

Open-Source Conversational AI with SpeechBrain 1.0

Titouan Parcollet

Adel Moumen

Sylvain de Langen

Peter William VanHarn Plantinga

Yingzhi Wang

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

Yingzhi Wang

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)