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

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

*この研究の対応する著者

研究成果: Conference article査読

抄録

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.

本文言語English
ページ(範囲)6753-6757
ページ数5
ジャーナルICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
2021-June
DOI
出版ステータスPublished - 2021
外部発表はい
イベント2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021 - Virtual, Toronto, Canada
継続期間: 2021 6 62021 6 11

ASJC Scopus subject areas

  • ソフトウェア
  • 信号処理
  • 電子工学および電気工学

フィンガープリント

「EAT: Enhanced ASR-TTS for self-supervised speech recognition」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル