Edinburgh’s End-to-End Multilingual Speech Translation System for IWSLT 2021

Biao Zhang, Rico Sennrich

Abstract
This paper describes Edinburgh’s submissions to the IWSLT2021 multilingual speech translation (ST) task. We aim at improving multilingual translation and zero-shot performance in the constrained setting (without using any extra training data) through methods that encourage transfer learning and larger capacity modeling with advanced neural components. We build our end-to-end multilingual ST model based on Transformer, integrating techniques including adaptive speech feature selection, language-specific modeling, multi-task learning, deep and big Transformer, sparsified linear attention and root mean square layer normalization. We adopt data augmentation using machine translation models for ST which converts the zero-shot problem into a zero-resource one. Experimental results show that these methods deliver substantial improvements, surpassing the official baseline by > 15 average BLEU and outperforming our cascading system by > 2 average BLEU. Our final submission achieves competitive performance (runner up).
Anthology ID:
2021.iwslt-1.19
Volume:
Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021)
Month:
August
Year:
2021
Address:
Bangkok, Thailand (online)
Editors:
Marcello Federico, Alex Waibel, Marta R. Costa-jussà, Jan Niehues, Sebastian Stuker, Elizabeth Salesky
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
Association for Computational Linguistics
Note:
Pages:
160–168
Language:
URL:
https://preview.aclanthology.org/icon-24-ingestion/2021.iwslt-1.19/
DOI:
10.18653/v1/2021.iwslt-1.19
Bibkey:
Cite (ACL):
Biao Zhang and Rico Sennrich. 2021. Edinburgh’s End-to-End Multilingual Speech Translation System for IWSLT 2021. In Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021), pages 160–168, Bangkok, Thailand (online). Association for Computational Linguistics.
Cite (Informal):
Edinburgh’s End-to-End Multilingual Speech Translation System for IWSLT 2021 (Zhang & Sennrich, IWSLT 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/icon-24-ingestion/2021.iwslt-1.19.pdf
PDF Search Fix data