English

EAT: Enhanced ASR-TTS for Self-supervised Speech Recognition

Audio and Speech Processing 2021-04-16 v1 Artificial Intelligence Machine Learning Sound

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\rightarrowTTS direction is equipped with a language model reward to penalize the ASR hypotheses before forwarding it to TTS. 2) In the TTS\rightarrowASR 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.

Keywords

Cite

@article{arxiv.2104.07474,
  title  = {EAT: Enhanced ASR-TTS for Self-supervised Speech Recognition},
  author = {Murali Karthick Baskar and Lukáš Burget and Shinji Watanabe and Ramon Fernandez Astudillo and Jan "Honza'' Černocký},
  journal= {arXiv preprint arXiv:2104.07474},
  year   = {2021}
}
R2 v1 2026-06-24T01:12:06.123Z