Login / Signup

Deep Visual Attributes vs. Hand-Crafted Audio Features on Multidomain Speech Emotion Recognition.

Michalis PapakostasEvaggelos SpyrouTheodoros GiannakopoulosGiorgos SiantikosDimitrios SgouropoulosPhivos MylonasFillia Makedon
Published in: Comput. (2017)
Keyphrases
  • deep learning
  • unsupervised learning
  • audio visual
  • visual features
  • low level
  • machine learning
  • search engine
  • image processing
  • multimedia
  • eye movements