Portrait de Ricard Marxer n'est pas disponible

Ricard Marxer

Collaborateur·rice de recherche - University of Toulon
Superviseur⋅e principal⋅e
Pablo Piantanida
Co-supervisor
Mirco Ravanelli
Sujets de recherche
Alignement de l'IA
Apprentissage automatique pour la parole et l'audio
Apprentissage de représentations
Apprentissage profond
Biodiversité
Cognition
IA conversationnelle
IA pour la créativité musicale
IA pour la science
Sécurité de l'IA
Traitement audio
Traitement du langage naturel
Site web
Google Scholar
GitHub

Publications

Discrete Audio Tokens: More Than a Survey!
Pooneh Mousavi
Gallil Maimon
Adel Moumen
Darius Petermann
Jiatong Shi
Haibin Wu
Haici Yang
Anastasia Kuznetsova
Artem Ploujnikov
Ricard Marxer
Bhuvana Ramabhadran
Benjamin Elizalde
Loren Lugosch
Jinyu Li
Cem Subakan
Phil Woodland
Minje Kim
Hung-yi Lee
Shinji Watanabe
Yossi Adi … (voir 1 de plus)
Mirco Ravanelli
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/.
2025-09-07
TMLR (accepté)
doi.org
openreview.net
Discrete Audio Tokens: More Than a Survey!
Pooneh Mousavi
Gallil Maimon
Adel Moumen
Darius Petermann
Jiatong Shi
Haibin Wu
Haici Yang
Anastasia Kuznetsova
Artem Ploujnikov
Ricard Marxer
Bhuvana Ramabhadran
Benjamin Elizalde
Loren Lugosch
Jinyu Li
Cem Subakan
Phil Woodland
Minje Kim
Hung-yi Lee
Shinji Watanabe
Yossi Adi … (voir 1 de plus)
Mirco Ravanelli
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)
arxiv.org
arxiv.org