Publication Details
BUT Systems for IWSLT 2023 Marathi - Hindi Low Resource Speech Translation Task
Beneš Karel, Ing. (DCGM)
Tikhonov Maksim, Bc.
Černocký Jan, prof. Dr. Ing. (DCGM)
Marathi, Hindi, Low Resource, Speech, Translation
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.
@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"
}