Login / Signup

Speaker adaptive bottleneck features extraction for LVCSR based on discriminative learning of speaker codes.

Changqing KongShaofei XueJianqing GaoWu GuoLi-Rong DaiHui Jiang
Published in: ISCSLP (2014)
Keyphrases
  • discriminative learning
  • features extraction
  • generative model
  • automatic classification
  • automatic speech recognition
  • maximum margin
  • machine learning
  • high quality
  • classification accuracy
  • information extraction