1 |
Source or target first? Comparison of two post-editing strategies with translation students
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-03546151 ; 2022 (2022)
|
|
BASE
|
|
Show details
|
|
2 |
Automatic Normalisation of Early Modern French
|
|
|
|
In: https://hal.inria.fr/hal-03540226 ; 2022 (2022)
|
|
BASE
|
|
Show details
|
|
3 |
Offline Corpus Augmentation for English-Amharic Machine Translation
|
|
|
|
In: 2022 The 5th International Conference on Information and Computer Technologies ; https://hal.archives-ouvertes.fr/hal-03547539 ; 2022 The 5th International Conference on Information and Computer Technologies, Mar 2022, New York, United States (2022)
|
|
BASE
|
|
Show details
|
|
4 |
DeepL et Google Translate face à l'ambiguïté phraséologique
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-03583995 ; 2022 (2022)
|
|
BASE
|
|
Show details
|
|
5 |
Language politics in international organisations ; Políticas lingüísticas en las organizaciones internacionales ; Politiques des langues dans les organisations internationales
|
|
|
|
In: ISSN: 0243-6450 ; EISSN: 1960-6001 ; Mots: les langages du politique ; https://halshs.archives-ouvertes.fr/halshs-03639374 ; Mots: les langages du politique, ENS Éditions (Lyon), 2022, 2022 (128), pp.9-25. ⟨10.4000/mots.29160⟩ (2022)
|
|
BASE
|
|
Show details
|
|
6 |
Le modèle Transformer: un « couteau suisse » pour le traitement automatique des langues
|
|
|
|
In: Techniques de l'Ingenieur ; https://hal.archives-ouvertes.fr/hal-03619077 ; Techniques de l'Ingenieur, Techniques de l'ingénieur, 2022, ⟨10.51257/a-v1-in195⟩ ; https://www.techniques-ingenieur.fr/base-documentaire/innovation-th10/innovations-en-electronique-et-tic-42257210/transformer-des-reseaux-de-neurones-pour-le-traitement-automatique-des-langues-in195/ (2022)
|
|
BASE
|
|
Show details
|
|
7 |
On the use of machine translation and topic-modeling to analyze non-parallel multilingual corpora: A case study in the history of philosophy of science ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
On the use of machine translation and topic-modeling to analyze non-parallel multilingual corpora: A case study in the history of philosophy of science ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Repository of psychological instruments in Serbian [Repozitorijum psiholoških instrumenata na srpskom jeziku] (REPOPSI) ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Hebrew Transformed: Machine Translation of Hebrew Using the Transformer Architecture
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Translation as a Communication Strategy in Representing National Culture
|
|
|
|
In: Social Inclusion ; 9 ; 1 ; 5-13 ; Social Inclusion and Multilingualism: The Impact of Linguistic Justice, Economy of Language and Language Policy (2022)
|
|
BASE
|
|
Show details
|
|
12 |
Isotopy as a Tool for the Analysis of Comics in Translation: The Italian 'Rip-Off' of Gilbert Shelton's Freak Brothers
|
|
|
|
In: Punctum: International Journal of Semiotics ; 7 ; 2 ; 17-43 (2022)
|
|
BASE
|
|
Show details
|
|
14 |
Predicting and Critiquing Machine Virtuosity: Mawwal Accompaniment as Case Study
|
|
|
|
In: International Computer Music Conference ; https://hal.archives-ouvertes.fr/hal-03044066 ; International Computer Music Conference, Jul 2021, Santiago, Chile (2021)
|
|
BASE
|
|
Show details
|
|
15 |
Investigating alignment interpretability for low-resource NMT
|
|
|
|
In: ISSN: 0922-6567 ; EISSN: 1573-0573 ; Machine Translation ; https://hal.archives-ouvertes.fr/hal-03139744 ; Machine Translation, Springer Verlag, 2021, ⟨10.1007/s10590-020-09254-w⟩ (2021)
|
|
BASE
|
|
Show details
|
|
16 |
Impact of Encoding and Segmentation Strategies on End-to-End Simultaneous Speech Translation
|
|
|
|
In: INTERSPEECH 2021 ; https://hal.archives-ouvertes.fr/hal-03372487 ; INTERSPEECH 2021, Aug 2021, Brno, Czech Republic (2021)
|
|
BASE
|
|
Show details
|
|
17 |
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
|
|
18 |
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: ; 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
|
|
19 |
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
|
|
20 |
Parallel Corpora Preparation for English-Amharic Machine Translation
|
|
|
|
In: IWANN 2021 - International Work on Artificial Neural Networks, Conference Springer LNCS proceedings ; https://hal.inria.fr/hal-03272258 ; IWANN 2021 - International Work on Artificial Neural Networks, Conference Springer LNCS proceedings, Jun 2021, Online, Spain (2021)
|
|
BASE
|
|
Show details
|
|
|
|