The NiuTrans End-to-End Speech Translation System for IWSLT23 English-to-Chinese Offline Task

Yuchen Han, Xiaoqian Liu, Hao Chen, Yuhao Zhang, Chen Xu, Tong Xiao, Jingbo Zhu


Abstract
This paper describes the NiuTrans end-to-end speech translation system submitted for the IWSLT 2023 English-to-Chinese offline task. Our speech translation models are composed of pre-trained ASR and MT models under the SATE framework. Several pre-trained models with diverse architectures and input representations (e.g., log Mel-filterbank and waveform) were utilized. We proposed an IDA method to iteratively improve the performance of the MT models and generate the pseudo ST data through MT systems. We then trained ST models with different structures and data settings to enhance ensemble performance. Experimental results demonstrate that our NiuTrans system achieved a BLEU score of 29.22 on the MuST-C En-Zh tst-COMMON set, outperforming the previous year’s submission by 0.12 BLEU despite using less MT training data.
Anthology ID:
2023.iwslt-1.17
Volume:
Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)
Month:
July
Year:
2023
Address:
Toronto, Canada (in-person and online)
Editors:
Elizabeth Salesky, Marcello Federico, Marine Carpuat
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
Association for Computational Linguistics
Note:
Pages:
211–218
Language:
URL:
https://aclanthology.org/2023.iwslt-1.17
DOI:
10.18653/v1/2023.iwslt-1.17
Bibkey:
Cite (ACL):
Yuchen Han, Xiaoqian Liu, Hao Chen, Yuhao Zhang, Chen Xu, Tong Xiao, and Jingbo Zhu. 2023. The NiuTrans End-to-End Speech Translation System for IWSLT23 English-to-Chinese Offline Task. In Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023), pages 211–218, Toronto, Canada (in-person and online). Association for Computational Linguistics.
Cite (Informal):
The NiuTrans End-to-End Speech Translation System for IWSLT23 English-to-Chinese Offline Task (Han et al., IWSLT 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/landing_page/2023.iwslt-1.17.pdf