Detail publikace

Eat: Enhanced ASR-TTS for Self-Supervised Speech Recognition

BASKAR, M. BURGET, L. WATANABE, S. ASTUDILLO, R. ČERNOCKÝ, J.

Originální název

Eat: Enhanced ASR-TTS for Self-Supervised Speech Recognition

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

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-ofdomain 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.

Klíčová slova

cycle-consistency, self-supervision, sequence-tosequence, speech recognition

Autoři

BASKAR, M.; BURGET, L.; WATANABE, S.; ASTUDILLO, R.; ČERNOCKÝ, J.

Vydáno

6. 6. 2021

Nakladatel

IEEE Signal Processing Society

Místo

Toronto, Ontario

ISBN

978-1-7281-7605-5

Kniha

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Strany od

6753

Strany do

6757

Strany počet

5

URL

BibTex

@inproceedings{BUT175793,
  author="BASKAR, M. and BURGET, L. and WATANABE, S. and ASTUDILLO, R. and ČERNOCKÝ, J.",
  title="Eat: Enhanced ASR-TTS for Self-Supervised Speech Recognition",
  booktitle="ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)",
  year="2021",
  pages="6753--6757",
  publisher="IEEE Signal Processing Society",
  address="Toronto, Ontario",
  doi="10.1109/ICASSP39728.2021.9413375",
  isbn="978-1-7281-7605-5",
  url="https://ieeexplore.ieee.org/document/9413375"
}