Sign in

Speaker-invariant and rhythm-sensitive representation of spoken words.

Nobuaki MinematsuYousuke OzakiKeikichi HiroseDonna Erickson
Published in: APSIPA (2013)
Keyphrases
  • spoken words
  • automatic speech recognition
  • invariant representation
  • machine learning
  • multiscale
  • multi modal
  • image representation
  • translation invariant
  • image processing
  • affine invariant
  • invariant features