Login / Signup

Direct adaptation of hybrid DNN/HMM model for fast speaker adaptation in LVCSR based on speaker code.

Shaofei XueOssama Abdel-HamidHui JiangLi-Rong Dai
Published in: ICASSP (2014)
Keyphrases
  • speaker adaptation
  • speech recognition
  • hidden markov models
  • probabilistic model
  • neural network
  • high level
  • information extraction
  • video data