Emotion-Aware Audio-Driven Face Animation via Contrastive Feature Disentanglement.
Xin RenJuan LuoXionghu ZhongMinjie CaiPublished in: INTERSPEECH (2023)
Keyphrases
- multimodal fusion
- facial expressions
- emotion recognition
- audio visual
- multimedia
- cepstral features
- image features
- facial animation
- feature vectors
- high robustness
- data driven
- signal processing
- face images
- computer graphics
- visual information
- facial images
- recognition algorithm
- visual data
- relevance feedback
- human faces
- multi modal
- motion capture
- biometric systems
- virtual humans
- feature set