Login / Signup

Combination of multiple acoustic models with unsupervised adaptation for lecture speech transcription.

Peng ShenXugang LuXinhui HuNaoyuki KandaMasahiro SaikoChiori HoriHisashi Kawai
Published in: Speech Commun. (2016)
Keyphrases
  • supervised learning
  • unsupervised learning
  • training data
  • neural network
  • machine learning
  • multimedia
  • pattern recognition
  • multi modal
  • speech recognition