Login / Signup

Bridging Speech and Textual Pre-trained Models with Unsupervised ASR.

Jiatong ShiChan-Jan HsuHo-Lam ChungDongji GaoPaola GarcíaShinji WatanabeAnn LeeHung-yi Lee
Published in: CoRR (2022)
Keyphrases
  • pre trained
  • automatic speech recognition
  • speech recognition
  • prior knowledge
  • probabilistic model
  • noisy environments
  • real time
  • data sets
  • neural network
  • training data
  • supervised learning
  • speech signal