The NPU-MSXF Speech-to-Speech Translation System for IWSLT 2023 Speech-to-Speech Translation Task

Kun Song, Yi Lei, Peikun Chen, Yiqing Cao, Kun Wei, Yongmao Zhang, Lei Xie, Ning Jiang, Guoqing Zhao


Abstract
This paper describes the NPU-MSXF system for the IWSLT 2023 speech-to-speech translation (S2ST) task which aims to translate from English speech of multi-source to Chinese speech. The system is built in a cascaded manner consisting of automatic speech recognition (ASR), machine translation (MT), and text-to-speech (TTS). We make tremendous efforts to handle the challenging multi-source input. Specifically, to improve the robustness to multi-source speech input, we adopt various data augmentation strategies and a ROVER-based score fusion on multiple ASR model outputs. To better handle the noisy ASR transcripts, we introduce a three-stage fine-tuning strategy to improve translation accuracy. Finally, we build a TTS model with high naturalness and sound quality, which leverages a two-stage framework, using network bottleneck features as a robust intermediate representation for speaker timbre and linguistic content disentanglement. Based on the two-stage framework, pre-trained speaker embedding is leveraged as a condition to transfer the speaker timbre in the source English speech to the translated Chinese speech. Experimental results show that our system has high translation accuracy, speech naturalness, sound quality, and speaker similarity. Moreover, it shows good robustness to multi-source data.
Anthology ID:
2023.iwslt-1.29
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:
311–320
Language:
URL:
https://aclanthology.org/2023.iwslt-1.29
DOI:
10.18653/v1/2023.iwslt-1.29
Bibkey:
Cite (ACL):
Kun Song, Yi Lei, Peikun Chen, Yiqing Cao, Kun Wei, Yongmao Zhang, Lei Xie, Ning Jiang, and Guoqing Zhao. 2023. The NPU-MSXF Speech-to-Speech Translation System for IWSLT 2023 Speech-to-Speech Translation Task. In Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023), pages 311–320, Toronto, Canada (in-person and online). Association for Computational Linguistics.
Cite (Informal):
The NPU-MSXF Speech-to-Speech Translation System for IWSLT 2023 Speech-to-Speech Translation Task (Song et al., IWSLT 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.iwslt-1.29.pdf