Leveraging Pseudo-labeled Data to Improve Direct Speech-to-Speech Translation

18 May 2022  ·  Qianqian Dong, Fengpeng Yue, Tom Ko, Mingxuan Wang, Qibing Bai, Yu Zhang ·

Direct Speech-to-speech translation (S2ST) has drawn more and more attention recently. The task is very challenging due to data scarcity and complex speech-to-speech mapping. In this paper, we report our recent achievements in S2ST. Firstly, we build a S2ST Transformer baseline which outperforms the original Translatotron. Secondly, we utilize the external data by pseudo-labeling and obtain a new state-of-the-art result on the Fisher English-to-Spanish test set. Indeed, we exploit the pseudo data with a combination of popular techniques which are not trivial when applied to S2ST. Moreover, we evaluate our approach on both syntactically similar (Spanish-English) and distant (English-Chinese) language pairs. Our implementation is available at https://github.com/fengpeng-yue/speech-to-speech-translation.

PDF Abstract

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.