The USTC-NELSLIP Offline Speech Translation Systems for IWSLT 2022

Weitai Zhang, Zhongyi Ye, Haitao Tang, Xiaoxi Li, Xinyuan Zhou, Jing Yang, Jianwei Cui, Pan Deng, Mohan Shi, Yifan Song, Dan Liu, Junhua Liu, Lirong Dai


Abstract
This paper describes USTC-NELSLIP’s submissions to the IWSLT 2022 Offline Speech Translation task, including speech translation of talks from English to German, English to Chinese and English to Japanese. We describe both cascaded architectures and end-to-end models which can directly translate source speech into target text. In the cascaded condition, we investigate the effectiveness of different model architectures with robust training and achieve 2.72 BLEU improvements over last year’s optimal system on MuST-C English-German test set. In the end-to-end condition, we build models based on Transformer and Conformer architectures, achieving 2.26 BLEU improvements over last year’s optimal end-to-end system. The end-to-end system has obtained promising results, but it is still lagging behind our cascaded models.
Anthology ID:
2022.iwslt-1.15
Volume:
Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022)
Month:
May
Year:
2022
Address:
Dublin, Ireland (in-person and online)
Venues:
ACL | IWSLT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
198–207
Language:
URL:
https://aclanthology.org/2022.iwslt-1.15
DOI:
10.18653/v1/2022.iwslt-1.15
Bibkey:
Cite (ACL):
Weitai Zhang, Zhongyi Ye, Haitao Tang, Xiaoxi Li, Xinyuan Zhou, Jing Yang, Jianwei Cui, Pan Deng, Mohan Shi, Yifan Song, Dan Liu, Junhua Liu, and Lirong Dai. 2022. The USTC-NELSLIP Offline Speech Translation Systems for IWSLT 2022. In Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022), pages 198–207, Dublin, Ireland (in-person and online). Association for Computational Linguistics.
Cite (Informal):
The USTC-NELSLIP Offline Speech Translation Systems for IWSLT 2022 (Zhang et al., IWSLT 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.iwslt-1.15.pdf