Sign in

An Audio-Saliency Masking Transformer for Audio Emotion Classification in Movies.

Ya-Tse WuJeng-Lin LiChi-Chun Lee
Published in: ICASSP (2022)
Keyphrases
  • multimedia
  • emotion recognition
  • audio visual
  • visual information
  • emotion classification
  • visual data
  • broadcast news
  • training data
  • multi modal
  • audio features