Login / Signup

External Text Based Data Augmentation for Low-Resource Speech Recognition in the Constrained Condition of OpenASR21 Challenge.

Guolong ZhongHongyu SongRuoyu WangLei SunDiyuan LiuJia PanXin FangJun DuJie ZhangLirong Dai
Published in: INTERSPEECH (2022)
Keyphrases
  • speech recognition
  • training data
  • hidden markov models
  • language model
  • text classification
  • non stationary
  • speech processing