papers AI Learner
The Github is limit! Click to go to the new site.

Self-supervised Sequence-to-sequence ASR using Unpaired Speech and Text

2019-04-30
Murali Karthick Baskar, Shinji Watanabe, Ramon Astudillo, Takaaki Hori, Lukáš Burget, Jan Černocký

Abstract

Sequence-to-sequence ASR models require large quantities of data to attain high performance. For this reason, there has been a recent surge in interest for self-supervised and supervised training in such models. This work builds upon recent results showing notable improvements in self-supervised training using cycle-consistency and related techniques. Such techniques derive training procedures and losses able to leverage unpaired speech and/or text data by combining ASR with text-to-speech (TTS) models. In particular, this work proposes a new self-supervised loss combining an end-to-end differentiable ASR$\rightarrow$TTS loss with a point estimate TTS$\rightarrow$ASR loss. The method is able to leverage both unpaired speech and text data to outperform recently proposed related techniques in terms of \%WER. We provide extensive results analyzing the impact of data quantity and speech and text modalities and show consistent gains across WSJ and Librispeech corpora. Our code is provided to reproduce the experiments.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1905.01152

PDF

http://arxiv.org/pdf/1905.01152


Comments

Content