Using Auxiliary Tasks In Multimodal Fusion of Wav2vec 2.0 And Bert for Multimodal Emotion Recognition.

Dekai SunYancheng HeJiqing Han
Published in: ICASSP (2023)
Keyphrases
  • multimodal fusion
  • audio visual
  • emotion recognition
  • multi modal
  • emotional speech
  • visual information
  • high robustness
  • visual data
  • multimedia
  • relevance feedback
  • multimodal interfaces
  • gait recognition
  • affective states