1 |
Fine-tuning pre-trained models for Automatic Speech Recognition: experiments on a fieldwork corpus of Japhug (Trans-Himalayan family)
|
|
|
|
In: https://halshs.archives-ouvertes.fr/halshs-03647315 ; 2022 (2022)
|
|
BASE
|
|
Show details
|
|
2 |
Fine-tuning pre-trained models for Automatic Speech Recognition: experiments on a fieldwork corpus of Japhug (Trans-Himalayan family)
|
|
|
|
In: https://halshs.archives-ouvertes.fr/halshs-03647315 ; 2022 (2022)
|
|
BASE
|
|
Show details
|
|
3 |
LeBenchmark: A Reproducible Framework for Assessing Self-Supervised Representation Learning from Speech
|
|
Evain, Solène; Nguyen, Ha; Le, Hang; Zanon Boito, Marcely; Mdhaffar, Salima; Alisamir, Sina; Tong, Ziyi; Tomashenko, Natalia; Dinarelli, Marco; Parcollet, Titouan; Allauzen, Alexandre; Estève, Yannick; Lecouteux, Benjamin; Portet, François; Rossato, Solange; Ringeval, Fabien; Schwab, Didier; Besacier, Laurent
|
|
In: INTERSPEECH 2021: Conference of the International Speech Communication Association ; https://hal.archives-ouvertes.fr/hal-03317730 ; INTERSPEECH 2021: Conference of the International Speech Communication Association, Aug 2021, Brno, Czech Republic (2021)
|
|
Abstract:
International audience ; Self-Supervised Learning (SSL) using huge unlabeled data has been successfully explored for image and natural language processing. Recent works also investigated SSL from speech. They were notably successful to improve performance on downstream tasks such as automatic speech recognition (ASR). While these works suggest it is possible to reduce dependence on labeled data for building efficient speech systems, their evaluation was mostly made on ASR and using multiple and heterogeneous experimental settings (most of them for English). This questions the objective comparison of SSL approaches and the evaluation of their impact on building speech systems. In this paper, we propose LeBenchmark: a reproducible framework for assessing SSL from speech. It not only includes ASR (high and low resource) tasks but also spoken language understanding, speech translation and emotion recognition. We also focus on speech technologies in a language different than English: French. SSL models of different sizes are trained from carefully sourced and documented datasets. Experiments show that SSL is beneficial for most but not all tasks which confirms the need for exhaustive and reliable benchmarks to evaluate its real impact. LeBenchmark is shared with the scientific community for reproducible research in SSL from speech.
|
|
Keyword:
[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]; ASR; Automatic Emotion Recognition; Self-Supervised Representation Learning; SLU; Speech Translation
|
|
URL: https://hal.archives-ouvertes.fr/hal-03317730/file/FLOWBERT_IS2021.pdf https://hal.archives-ouvertes.fr/hal-03317730/document https://hal.archives-ouvertes.fr/hal-03317730
|
|
BASE
|
|
Hide details
|
|
4 |
LeBenchmark: A Reproducible Framework for Assessing Self-Supervised Representation Learning from Speech
|
|
|
|
In: INTERSPEECH 2021: ; INTERSPEECH 2021: Conference of the International Speech Communication Association ; https://hal.archives-ouvertes.fr/hal-03317730 ; INTERSPEECH 2021: Conference of the International Speech Communication Association, Aug 2021, Brno, Czech Republic (2021)
|
|
BASE
|
|
Show details
|
|
5 |
LeBenchmark: A Reproducible Framework for Assessing Self-Supervised Representation Learning from Speech
|
|
|
|
In: INTERSPEECH 2021: ; INTERSPEECH 2021: Conference of the International Speech Communication Association ; https://hal.archives-ouvertes.fr/hal-03317730 ; INTERSPEECH 2021: Conference of the International Speech Communication Association, Aug 2021, Brno, Czech Republic (2021)
|
|
BASE
|
|
Show details
|
|
6 |
Investigating the Impact of Gender Representation in ASR Training Data: a Case Study on Librispeech
|
|
|
|
In: Proceedings of the 3rd Workshop on Gender Bias in Natural Language Processing ; 3rd Workshop on Gender Bias in Natural Language Processing ; https://hal.univ-grenoble-alpes.fr/hal-03472117 ; 3rd Workshop on Gender Bias in Natural Language Processing, Aug 2021, Online, France. pp.86-92, ⟨10.18653/v1/2021.gebnlp-1.10⟩ (2021)
|
|
BASE
|
|
Show details
|
|
7 |
Proximité rythmique entre apprenants et natifs du français Évaluation d'une métrique basée sur le CEFC
|
|
|
|
In: Actes de la 6e conférence conjointe Journées d'Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition). Volume 1 : Journées d'Études sur la Parole ; 6e conférence conjointe Journées d'Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition). Volume 1 : Journées d'Études sur la Parole ; https://hal.archives-ouvertes.fr/hal-02798525 ; 6e conférence conjointe Journées d'Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition). Volume 1 : Journées d'Études sur la Parole, 2020, Nancy, France. pp.118-126 (2020)
|
|
BASE
|
|
Show details
|
|
8 |
Gender Representation in Open Source Speech Resources
|
|
|
|
In: LREC 2020 proceedings ; 12th Conference on Language Resources and Evaluation (LREC 2020) ; https://halshs.archives-ouvertes.fr/halshs-02899402 ; 12th Conference on Language Resources and Evaluation (LREC 2020), May 2020, Marseille, France. pp.6599-6605 (2020)
|
|
BASE
|
|
Show details
|
|
9 |
Exploration des compétences langagières en maternelle
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-03534211 ; 2020 (2020)
|
|
BASE
|
|
Show details
|
|
10 |
Coarticulatory Aspects of the Fluent Speech of French and Italian People Who Stutter Under Altered Auditory Feedback
|
|
|
|
In: Front Psychol (2020)
|
|
BASE
|
|
Show details
|
|
11 |
Atividade docente e Educação Especial: dos encaminhamentos históricos ao contraponto Histórico-Cultural
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Why do syllable onsets attract consonant(s)?
|
|
|
|
In: ISSN: 1120-2726 ; EISSN: 0390-6809 ; Italian Journal of Linguistics / Rivista di linguistica ; https://hal.archives-ouvertes.fr/hal-01212119 ; Italian Journal of Linguistics / Rivista di linguistica, Pacini Editore S.p.A, 2015, 27 (1), pp.133-160 (2015)
|
|
BASE
|
|
Show details
|
|
16 |
Structures syllabiques et caractéristiques du cycle mandibulaire : une étude articulatoire des asymétries
|
|
|
|
In: JEP 2014 - 30e Journées d'Etudes sur la Parole ; https://hal.archives-ouvertes.fr/hal-01017075 ; JEP 2014 - 30e Journées d'Etudes sur la Parole, Jun 2014, Le Mans, France. pp.29 (2014)
|
|
BASE
|
|
Show details
|
|
17 |
O ensino da escrita e o desenvolvimento das pessoas com deficiência intelectual
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Bégaiement chez des adultes bègues français et italiens. Aspects disfluents et fluents dans deux conditions perceptives
|
|
|
|
In: Bilinguisme et biculture : nouveaux défis ? ; https://hal.archives-ouvertes.fr/hal-00835404 ; Sous la direction Peggy Gatignol & Sylvia Topouzkhanian. Responsables scientifiques des XIIèmes Rencontres Internationales d'Orthophonie. Bilinguisme et biculture : nouveaux défis ?, Ortho Edition, pp.117-143, 2012, 978-2-36235-039-9 (2012)
|
|
BASE
|
|
Show details
|
|
19 |
La produzione di sillabe nella balbuzie in condizioni di feedback uditivo normale e alterato
|
|
|
|
In: International Conference on Stuttering ; https://hal.archives-ouvertes.fr/hal-00835401 ; International Conference on Stuttering, Jun 2012, Rome, Italy. pp.177-188 (2012)
|
|
BASE
|
|
Show details
|
|
20 |
Speaker verification by inexperienced and experienced listeners vs. speaker verification system
|
|
|
|
In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) ; https://hal.archives-ouvertes.fr/hal-01317620 ; IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2011, Prague, Czech Republic. ⟨10.1109/ICASSP.2011.5947707⟩ (2011)
|
|
BASE
|
|
Show details
|
|
|
|