Publication detail

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

KESIRAJU, S. BENEŠ, K. TIKHONOV, M. ČERNOCKÝ, J.

Original Title

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

Type

conference paper

Language

English

Original 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 finetuned 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.

Keywords

Marathi, Hindi, Low Resource, Speech, Translation

Authors

KESIRAJU, S.; BENEŠ, K.; TIKHONOV, M.; ČERNOCKÝ, J.

Released

9. 7. 2023

Publisher

Association for Computational Linguistics

Location

Toronto (in-person and online)

ISBN

978-1-959429-84-5

Book

20th International Conference on Spoken Language Translation, IWSLT 2023 - Proceedings of the Conference

Pages from

227

Pages to

234

Pages count

8

URL

https://aclanthology.org/2023.iwslt-1.19.pdf

BibTex

@inproceedings{BUT185198,
  author="Santosh {Kesiraju} and Karel {Beneš} and Maksim {Tikhonov} and Jan {Černocký}",
  title="BUT Systems for IWSLT 2023 Marathi - Hindi Low Resource Speech Translation Task",
  booktitle="20th International Conference on Spoken Language Translation, IWSLT 2023 -  Proceedings of the Conference",
  year="2023",
  pages="227--234",
  publisher="Association for Computational Linguistics",
  address="Toronto (in-person and online)",
  doi="10.18653/v1/2023.iwslt-1.19",
  isbn="978-1-959429-84-5",
  url="https://aclanthology.org/2023.iwslt-1.19.pdf"
}