| 1 |
Using Automatic Speech Recognition to Optimize Hearing-Aid Time Constants
|
|
|
|
In: ISSN: 1662-4548 ; EISSN: 1662-453X ; Frontiers in Neuroscience ; https://hal.archives-ouvertes.fr/hal-03627441 ; Frontiers in Neuroscience, Frontiers, 2022, 16 (779062), ⟨10.3389/fnins.2022.779062⟩ ; https://www.frontiersin.org/articles/10.3389/fnins.2022.779062/full (2022)
|
|
BASE
|
|
Show details
|
|
|
| 2 |
Treasure Hunters 2: exploration of speech training efficacy ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 3 |
Automatic Speech Recognition Performance Improvement for Mandarin Based on Optimizing Gain Control Strategy
|
|
|
|
In: Sensors; Volume 22; Issue 8; Pages: 3027 (2022)
|
|
BASE
|
|
Show details
|
|
|
| 4 |
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
|
|
|
| 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 |
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
|
|
|
| 7 |
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
|
|
|
| 8 |
Large vocabulary automatic speech recognition: from hybrid to end-to-end approaches ; Reconnaissance automatique de la parole à large vocabulaire : des approches hybrides aux approches End-to-End
|
|
|
|
In: https://hal.archives-ouvertes.fr/tel-03269807 ; Son [cs.SD]. Université toulouse 3 Paul Sabatier, 2021. Français (2021)
|
|
BASE
|
|
Show details
|
|
|
| 9 |
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
|
|
|
| 10 |
Discriminative feature modeling for statistical speech recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 11 |
Repairing Swedish Automatic Speech Recognition ; Korrigering av Automatisk Taligenkänning för Svenska
|
|
Rehn, Karla. - : KTH, Skolan för elektroteknik och datavetenskap (EECS), 2021
|
|
BASE
|
|
Show details
|
|
|
| 12 |
Performance and Efficiency Evaluation of ASR Inference on the Edge
|
|
|
|
In: Sustainability ; Volume 13 ; Issue 22 (2021)
|
|
BASE
|
|
Show details
|
|
|
| 13 |
Domain-Adversarial Based Model with Phonological Knowledge for Cross-Lingual Speech Recognition
|
|
|
|
In: Electronics; Volume 10; Issue 24; Pages: 3172 (2021)
|
|
BASE
|
|
Show details
|
|
|
| 14 |
Improving Grapheme-to-Phoneme Conversion for Anglicisms in German Speech Recognition
|
|
|
|
In: Fraunhofer IAIS (2021)
|
|
BASE
|
|
Show details
|
|
|
| 15 |
Discovering structure in speech recordings: Unsupervised learning of word and phoneme like units for automatic speech recognition
|
|
|
|
In: Fraunhofer IAIS (2021)
|
|
BASE
|
|
Show details
|
|
|
| 16 |
Closed Captions: generador de subtítulos automáticos offline empleando un motor de conversión de voz a texto (STT)
|
|
|
|
BASE
|
|
Show details
|
|
|
| 17 |
Online Speech Recognition Using Multichannel Parallel Acoustic Score Computation and Deep Neural Network (DNN)- Based Voice-Activity Detector
|
|
|
|
In: Applied Sciences ; Volume 10 ; Issue 12 (2020)
|
|
BASE
|
|
Show details
|
|
|
| 18 |
Articulation modelling of vowels in dysarthric and non-dysarthric speech
|
|
|
|
BASE
|
|
Show details
|
|
|
| 19 |
Extractive Text-Based Summarization of Arabic videos: Issues, Approaches and Evaluations
|
|
|
|
In: ICALP: International Conference on Arabic Language Processing ; https://hal.archives-ouvertes.fr/hal-02314238 ; ICALP: International Conference on Arabic Language Processing, Oct 2019, Nancy, France. pp.65-78, ⟨10.1007/978-3-030-32959-4_5⟩ (2019)
|
|
BASE
|
|
Show details
|
|
|
| 20 |
Using automatic speech recognition for the prediction of impaired speech identification
|
|
|
|
In: 11th Speech in Noise Workshop (SPiN 2019) ; https://hal.archives-ouvertes.fr/hal-02976603 ; 11th Speech in Noise Workshop (SPiN 2019), Jan 2019, Ghent, Belgium ; https://spin2019.be/?p=program&id=88 (2019)
|
|
BASE
|
|
Show details
|
|
|
|
|
