EAT: Enhanced ASR-TTS for self-supervised speech recognition

Murali Karthick Baskar*, Lukáš Burget, Shinji Watanabe, Ramon Fernandez Astudillo, Jan Černocký

*Corresponding author for this work

Research output: Contribution to journalConference articlepeer-review

Abstract

Self-supervised ASR-TTS models suffer in out-of-domain data conditions. Here we propose an enhanced ASR-TTS (EAT) model that incorporates two main features: 1) The ASR→TTS direction is equipped with a language model reward to penalize the ASR hypotheses before forwarding it to TTS. 2) In the TTS→ASR direction, a hyper-parameter is introduced to scale the attention context from synthesized speech before sending it to ASR to handle out-of-domain data. Training strategies and the effectiveness of the EAT model are explored under out-of-domain data conditions. The results show that EAT reduces the performance gap between supervised and self-supervised training significantly by absolute 2.6% and 2.7% on Librispeech and BABEL respectively.

Original languageEnglish
Pages (from-to)6753-6757
Number of pages5
JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2021-June
DOIs
Publication statusPublished - 2021
Externally publishedYes
Event2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021 - Virtual, Toronto, Canada
Duration: 2021 Jun 62021 Jun 11

Keywords

  • Cycle-consistency
  • Self-supervision
  • Sequence-to-sequence
  • Speech recognition

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'EAT: Enhanced ASR-TTS for self-supervised speech recognition'. Together they form a unique fingerprint.

Cite this