DialogueSMM: Emotion Recognition in Conversation with Speaker-Aware Multimodal Multi-head Attention.
Changyong NiuShuo XuYuxiang JiaHongying ZanPublished in: NLPCC (2) (2023)
Keyphrases
- emotion recognition
- audio visual
- speaker verification
- multi modal
- visual information
- emotional speech
- visual data
- multi stream
- physiological signals
- multimedia
- speaker recognition
- natural language
- visual attention
- emotion classification
- human computer interaction
- information fusion
- machine learning
- facial expressions
- audio features
- feature extraction