Detail publikace

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

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

Originální název

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

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

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.

Klíčová slova

Marathi, Hindi, Low Resource, Speech, Translation

Autoři

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

Vydáno

9. 7. 2023

Nakladatel

Association for Computational Linguistics

Místo

Toronto (in-person and online)

ISBN

978-1-959429-84-5

Kniha

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

Strany od

227

Strany do

234

Strany počet

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"
}