The NiuTrans’s Submission to the IWSLT22 English-to-Chinese Offline Speech Translation Task
Yuhao Zhang, Canan Huang, Chen Xu, Xiaoqian Liu, Bei Li, Anxiang Ma, Tong Xiao, Jingbo Zhu
Abstract
This paper describes NiuTrans’s submission to the IWSLT22 English-to-Chinese (En-Zh) offline speech translation task. The end-to-end and bilingual system is built by constrained English and Chinese data and translates the English speech to Chinese text without intermediate transcription. Our speech translation models are composed of different pre-trained acoustic models and machine translation models by two kinds of adapters. We compared the effect of the standard speech feature (e.g. log Mel-filterbank) and the pre-training speech feature and try to make them interact. The final submission is an ensemble of three potential speech translation models. Our single best and ensemble model achieves 18.66 BLEU and 19.35 BLEU separately on MuST-C En-Zh tst-COMMON set.- Anthology ID:
- 2022.iwslt-1.19
- Volume:
- Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022)
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland (in-person and online)
- Editors:
- Elizabeth Salesky, Marcello Federico, Marta Costa-jussà
- Venue:
- IWSLT
- SIG:
- SIGSLT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 232–238
- Language:
- URL:
- https://aclanthology.org/2022.iwslt-1.19
- DOI:
- 10.18653/v1/2022.iwslt-1.19
- Cite (ACL):
- Yuhao Zhang, Canan Huang, Chen Xu, Xiaoqian Liu, Bei Li, Anxiang Ma, Tong Xiao, and Jingbo Zhu. 2022. The NiuTrans’s Submission to the IWSLT22 English-to-Chinese Offline Speech Translation Task. In Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022), pages 232–238, Dublin, Ireland (in-person and online). Association for Computational Linguistics.
- Cite (Informal):
- The NiuTrans’s Submission to the IWSLT22 English-to-Chinese Offline Speech Translation Task (Zhang et al., IWSLT 2022)
- PDF:
- https://preview.aclanthology.org/landing_page/2022.iwslt-1.19.pdf