Leveraging unsupervised and weakly-supervised data to improve direct speech-to-speech translation. (arXiv:2203.13339v2 [cs.CL] UPDATED)

End-to-end speech-to-speech translation (S2ST) without relying on
intermediate text representations is a rapidly emerging frontier of research.
Recent works have demonstrated that the performance of such direct S2ST systems
is approaching that of conventional cascade S2ST when trained on comparable
datasets. However, in practice, the performance of direct S2ST is bounded by
the availability of paired S2ST training data. In this work, we explore
multiple approaches for leveraging much more widely available unsupervised and
weakly-supervised speech and text data to …

arxiv data speech translation unsupervised weakly-supervised