Login / Signup

Sequence-to-sequence models for punctuated transcription combining lexical and acoustic features.

Ondrej KlejchPeter BellSteve Renals
Published in: ICASSP (2017)
Keyphrases
  • machine learning
  • low level
  • probabilistic model
  • acoustic features
  • neural network
  • multimedia
  • denoising
  • structured data
  • music genre classification