Login / Signup

Robust seed model training for speaker adaptation using pseudo-speaker features generated by inverse CMLLR transformation.

Arata ItohSunao HaraNorihide KitaokaKazuya Takeda
Published in: ASRU (2011)
Keyphrases
  • probabilistic model
  • neural network
  • computer vision
  • high level
  • pattern recognition
  • low level
  • maximum likelihood
  • feature set
  • speech recognition
  • speaker adaptation