Login / Signup

Towards Online-Recognition with Deep Bidirectional LSTM Acoustic Models.

Albert ZeyerRalf SchlüterHermann Ney
Published in: INTERSPEECH (2016)
Keyphrases
  • pattern recognition
  • speaker independent
  • speech recognition
  • acoustic models
  • character recognition
  • neural network
  • feature extraction
  • multi modal
  • computer vision
  • multimedia
  • hidden markov models
  • speech recognizer