The HW-TSC’s Offline Speech Translation System for IWSLT 2022 Evaluation

Yinglu Li, Minghan Wang, Jiaxin Guo, Xiaosong Qiao, Yuxia Wang, Daimeng Wei, Chang Su, Yimeng Chen, Min Zhang, Shimin Tao, Hao Yang, Ying Qin


Abstract
This paper describes the HW-TSC’s designation of the Offline Speech Translation System submitted for IWSLT 2022 Evaluation. We explored both cascade and end-to-end system on three language tracks (en-de, en-zh and en-ja), and we chose the cascade one as our primary submission. For the automatic speech recognition (ASR) model of cascade system, there are three ASR models including Conformer, S2T-Transformer and U2 trained on the mixture of five datasets. During inference, transcripts are generated with the help of domain controlled generation strategy. Context-aware reranking and ensemble based anti-interference strategy are proposed to produce better ASR outputs. For machine translation part, we pretrained three translation models on WMT21 dataset and fine-tuned them on in-domain corpora. Our cascade system shows competitive performance than the known offline systems in the industry and academia.
Anthology ID:
2022.iwslt-1.20
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:
239–246
Language:
URL:
https://aclanthology.org/2022.iwslt-1.20
DOI:
10.18653/v1/2022.iwslt-1.20
Bibkey:
Cite (ACL):
Yinglu Li, Minghan Wang, Jiaxin Guo, Xiaosong Qiao, Yuxia Wang, Daimeng Wei, Chang Su, Yimeng Chen, Min Zhang, Shimin Tao, Hao Yang, and Ying Qin. 2022. The HW-TSC’s Offline Speech Translation System for IWSLT 2022 Evaluation. In Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022), pages 239–246, Dublin, Ireland (in-person and online). Association for Computational Linguistics.
Cite (Informal):
The HW-TSC’s Offline Speech Translation System for IWSLT 2022 Evaluation (Li et al., IWSLT 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.iwslt-1.20.pdf
Data
LibriSpeech