Leveraging Pseudo-labeled Data to Improve Direct Speech-to-Speech Translation. (arXiv:2205.08993v1 [cs.CL])

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 …

arxiv data speech translation