Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                

BUT Systems for IWSLT 2023 Marathi - Hindi Low Resource Speech Translation Task

Santosh Kesiraju, Karel Beneš, Maksim Tikhonov, Jan Černocký


Abstract
This paper describes the systems submitted for Marathi to Hindi low-resource speech translation task. Our primary submission is based on an end-to-end direct speech translation system, whereas the contrastive one is a cascaded system. The backbone of both the systems is a Hindi-Marathi bilingual ASR system trained on 2790 hours of imperfect transcribed speech. The end-to-end speech translation system was directly initialized from the ASR, and then fine-tuned for direct speech translation with an auxiliary CTC loss for translation. The MT model for the cascaded system is initialized from a cross-lingual language model, which was then fine-tuned using 1.6 M parallel sentences. All our systems were trained from scratch on publicly available datasets. In the end, we use a language model to re-score the n-best hypotheses. Our primary submission achieved 30.5 and 39.6 BLEU whereas the contrastive system obtained 21.7 and 28.6 BLEU on official dev and test sets respectively. The paper also presents the analysis on several experiments that were conducted and outlines the strategies for improving speech translation in low-resource scenarios.
Anthology ID:
2023.iwslt-1.19
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:
227–234
Language:
URL:
https://aclanthology.org/2023.iwslt-1.19
DOI:
10.18653/v1/2023.iwslt-1.19
Bibkey:
Cite (ACL):
Santosh Kesiraju, Karel Beneš, Maksim Tikhonov, and Jan Černocký. 2023. BUT Systems for IWSLT 2023 Marathi - Hindi Low Resource Speech Translation Task. In Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023), pages 227–234, Toronto, Canada (in-person and online). Association for Computational Linguistics.
Cite (Informal):
BUT Systems for IWSLT 2023 Marathi - Hindi Low Resource Speech Translation Task (Kesiraju et al., IWSLT 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.iwslt-1.19.pdf