Login / Signup

Parallel phonetically aware DNNs and LSTM-RNNS for frame-by-frame discriminative modeling of spoken language identification.

Ryo MasumuraTaichi AsamiHirokazu MasatakiYushi Aono
Published in: ICASSP (2017)
Keyphrases
  • language identification
  • recurrent neural networks
  • speech recognition
  • information retrieval
  • image processing
  • video frames
  • image segmentation
  • multimedia
  • semi supervised
  • gray scale