ON-TRAC consortium systems for the IWSLT 2023 dialectal and low-resource speech translation tasks - Le Mans Université Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

ON-TRAC consortium systems for the IWSLT 2023 dialectal and low-resource speech translation tasks

Résumé

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 pre-trained SAMU-XLSR model as a speech encoder and an 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 a multilingual text dataset. This architecture allows us to improve the input speech representations and achieve significant improvements compared to conventional endto-end speech translation systems.
Fichier principal
Vignette du fichier
Laurent23.pdf (181.33 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04155208 , version 1 (07-07-2023)

Identifiants

  • HAL Id : hal-04155208 , version 1

Citer

Antoine Laurent, Souhir Gahbiche, Ha Nguyen, Haroun Elleuch, Fethi Bougares, et al.. ON-TRAC consortium systems for the IWSLT 2023 dialectal and low-resource speech translation tasks. International Conference on Spoken Language Translation (IWSLT) 2023, Jul 2023, Toronto, Canada. ⟨hal-04155208⟩
93 Consultations
109 Téléchargements

Partager

Gmail Facebook X LinkedIn More