WACO: Word-Aligned Contrastive Learning for Speech Translation

Siqi Ouyang, Rong Ye, Lei Li


Abstract
End-to-end Speech Translation (E2E ST) aims to directly translate source speech into target text. Existing ST methods perform poorly when only extremely small speech-text data are available for training. We observe that an ST model’s performance closely correlates with its embedding similarity between speech and source transcript. In this paper, we propose Word-Aligned COntrastive learning (WACO), a simple and effective method for extremely low-resource speech-to-text translation. Our key idea is bridging word-level representations for both speech and text modalities via contrastive learning. We evaluate WACO and other methods on the MuST-C dataset, a widely used ST benchmark, and on a low-resource direction Maltese-English from IWSLT 2023. Our experiments demonstrate that WACO outperforms the best baseline by 9+ BLEU points with only 1-hour parallel ST data. Code is available at https://github.com/owaski/WACO.
Anthology ID:
2023.acl-long.216
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3891–3907
Language:
URL:
https://aclanthology.org/2023.acl-long.216
DOI:
10.18653/v1/2023.acl-long.216
Bibkey:
Cite (ACL):
Siqi Ouyang, Rong Ye, and Lei Li. 2023. WACO: Word-Aligned Contrastive Learning for Speech Translation. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3891–3907, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
WACO: Word-Aligned Contrastive Learning for Speech Translation (Ouyang et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-long.216.pdf
Video:
 https://aclanthology.org/2023.acl-long.216.mp4