most citedSpeaker consistency loss and step-wise optimization for semi-supervised joint training of TTS and ASR using unpaired text data

1 citations · 1 across the 1 of their papers we have counts for

collaborators
Showing cs.SDShow all

1 paper · 1 filter

cs.SD2022★ 1 cited

Speaker consistency loss and step-wise optimization for semi-supervised joint training of TTS and ASR using unpaired text data

Naoki Makishima, Satoshi Suzuki, Atsushi Ando +1

In this paper, we investigate the semi-supervised joint training of text to speech (TTS) and automatic speech recognition (ASR), where a small amount of paired data and a large amo…