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.
|ジャーナル||ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings|
|出版ステータス||Published - 2021|
|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月 6 → 2021 6月 11
ASJC Scopus subject areas