DE eng

Search in the Catalogues and Directories

Hits 1 – 16 of 16

1
LeBenchmark: A Reproducible Framework for Assessing Self-Supervised Representation Learning from Speech
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)
BASE
Show details
2
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)
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-03317730v3/document
https://hal.archives-ouvertes.fr/hal-03317730v3/file/FLOWBERT_IS2021%282%29.pdf
https://hal.archives-ouvertes.fr/hal-03317730
BASE
Hide details
3
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
4
Recognizing lexical units in low-resource language contexts with supervised and unsupervised neural networks
In: https://hal.archives-ouvertes.fr/hal-03429051 ; [Research Report] LACITO (UMR 7107). 2021 (2021)
BASE
Show details
5
Supplementary material to the paper The VoicePrivacy 2020 Challenge: Results and findings
In: https://hal.archives-ouvertes.fr/hal-03335126 ; 2021 (2021)
BASE
Show details
6
Supplementary material to the paper The VoicePrivacy 2020 Challenge: Results and findings
In: https://hal.archives-ouvertes.fr/hal-03335126 ; 2021 (2021)
BASE
Show details
7
The VoicePrivacy 2020 Challenge: Results and findings
In: https://hal.archives-ouvertes.fr/hal-03332224 ; 2021 (2021)
BASE
Show details
8
Supplementary material to the paper The VoicePrivacy 2020 Challenge: Results and findings
In: https://hal.archives-ouvertes.fr/hal-03335126 ; 2021 (2021)
BASE
Show details
9
The VoicePrivacy 2020 Challenge: Results and findings
In: https://hal.archives-ouvertes.fr/hal-03332224 ; 2021 (2021)
BASE
Show details
10
Supplementary material to the paper The VoicePrivacy 2020 Challenge: Results and findings
In: https://hal.archives-ouvertes.fr/hal-03335126 ; 2021 (2021)
BASE
Show details
11
Supplementary material to the paper The VoicePrivacy 2020 Challenge: Results and findings
In: https://hal.archives-ouvertes.fr/hal-03335126 ; 2021 (2021)
BASE
Show details
12
The VoicePrivacy 2020 Challenge: Results and findings
In: https://hal.archives-ouvertes.fr/hal-03332224 ; 2021 (2021)
BASE
Show details
13
User-friendly automatic transcription of low-resource languages: Plugging ESPnet into Elpis
In: ComputEL-4: Fourth Workshop on the Use of Computational Methods in the Study of Endangered Languages ; https://halshs.archives-ouvertes.fr/halshs-03030529 ; ComputEL-4: Fourth Workshop on the Use of Computational Methods in the Study of Endangered Languages, Mar 2021, Hawai‘i, United States (2021)
BASE
Show details
14
Transdisciplinary Analysis of a Corpus of French Newsreels: The ANTRACT Project
In: ISSN: 1938-4122 ; Digital Humanities Quarterly ; https://hal.archives-ouvertes.fr/hal-03166755 ; Digital Humanities Quarterly, Alliance of Digital Humanities, 2021, Special Issue on AudioVisual Data in DH, 15 (1) ; http://digitalhumanities.org/dhq/ (2021)
BASE
Show details
15
Recognizing lexical units in low-resource language contexts with supervised and unsupervised neural networks
In: https://hal.archives-ouvertes.fr/hal-03429051 ; [Research Report] LACITO (UMR 7107). 2021 (2021)
BASE
Show details
16
User-friendly automatic transcription of low-resource languages: Plugging ESPnet into Elpis
In: ComputEL-4: Fourth Workshop on the Use of Computational Methods in the Study of Endangered Languages ; https://halshs.archives-ouvertes.fr/halshs-03030529 ; ComputEL-4: Fourth Workshop on the Use of Computational Methods in the Study of Endangered Languages, Mar 2021, Hawai‘i, United States (2021)
BASE
Show details

Catalogues
0
0
0
0
0
0
0
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
16
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern