Login / Signup

Alignment-Learning Based Single-Step Decoding for Accurate and Fast Non-Autoregressive Speech Recognition.

Yonghe WangRui LiuFeilong BaoHui ZhangGuanglai Gao
Published in: ICASSP (2022)
Keyphrases
  • speech recognition
  • autoregressive
  • hidden markov models
  • single step
  • pattern recognition
  • machine learning
  • language model
  • speech synthesis
  • speech signal
  • multiscale
  • active learning
  • least squares
  • speech recognizer