LivelySpeaker: Towards Semantic-Aware Co-Speech Gesture Generation.
Yihao ZhiXiaodong CunXuelin ChenXi ShenWen GuoShaoli HuangShenghua GaoPublished in: CoRR (2023)
Keyphrases
- multimodal interfaces
- speech recognition
- gesture recognition
- hand movements
- audio visual
- speech signal
- multi stream
- generation process
- human computer interaction
- automatic speech recognition
- pattern recognition
- data sets
- visual information
- database
- sign language
- generation method
- spoken language
- hand gesture recognition
- neural network