EmoTalk: Speech-driven emotional disentanglement for 3D face animation.
Ziqiao PengHaoyu WuZhenbo SongHao XuXiangyu ZhuHongyan LiuJun HeZhaoxin FanPublished in: CoRR (2023)
Keyphrases
- facial animation
- affect sensing
- facial expressions
- emotion recognition
- emotional state
- speech recognition
- face recognition
- human faces
- recognition algorithm
- motion capture data
- facial images
- audio visual
- face model
- speech synthesis
- data driven
- emotional intelligence
- facial features
- face images
- special effects
- recognition engine
- audio stream
- speaker recognition
- three dimensional
- head motion
- temporal coherence
- pattern recognition
- affective states
- computer vision
- speech signal
- face detection