ON-TRAC Consortium Systems for the IWSLT 2023 Dialectal and Low-resource Speech Translation Tasks

Antoine Laurent, Souhir Gahbiche, Ha Nguyen, Haroun Elleuch, Fethi Bougares, Antoine Thiol, Hugo Riguidel, Salima Mdhaffar, Gaëlle Laperrière, Lucas Maison, Sameer Khurana, Yannick Estève

Abstract
This paper describes the ON-TRAC consortium speech translation systems developed for IWSLT 2023 evaluation campaign. Overall, we participated in three speech translation tracks featured in the low-resource and dialect speech translation shared tasks, namely; i) spoken Tamasheq to written French, ii) spoken Pashto to written French, and iii) spoken Tunisian to written English. All our primary submissions are based on the end-to-end speech-to-text neural architecture using a pretrained SAMU-XLSR model as a speech encoder and a mbart model as a decoder. The SAMU-XLSR model is built from the XLS-R 128 in order to generate language agnostic sentence-level embeddings. This building is driven by the LaBSE model trained on multilingual text dataset. This architecture allows us to improve the input speech representations and achieve significant improvements compared to conventional end-to-end speech translation systems.
Anthology ID:
2023.iwslt-1.18
Volume:
Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)
Month:
July
Year:
2023
Address:
Toronto, Canada (in-person and online)
Editors:
Elizabeth Salesky, Marcello Federico, Marine Carpuat
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
Association for Computational Linguistics
Note:
Pages:
219–226
Language:
URL:
https://aclanthology.org/2023.iwslt-1.18
DOI:
10.18653/v1/2023.iwslt-1.18
Bibkey:
Cite (ACL):
Antoine Laurent, Souhir Gahbiche, Ha Nguyen, Haroun Elleuch, Fethi Bougares, Antoine Thiol, Hugo Riguidel, Salima Mdhaffar, Gaëlle Laperrière, Lucas Maison, Sameer Khurana, and Yannick Estève. 2023. ON-TRAC Consortium Systems for the IWSLT 2023 Dialectal and Low-resource Speech Translation Tasks. In Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023), pages 219–226, Toronto, Canada (in-person and online). Association for Computational Linguistics.
Cite (Informal):
ON-TRAC Consortium Systems for the IWSLT 2023 Dialectal and Low-resource Speech Translation Tasks (Laurent et al., IWSLT 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp22-frontmatter/2023.iwslt-1.18.pdf
PDF Search