SEEG: Semantic Energized Co-speech Gesture Generation.
Yuanzhi LiangQianyu FengLinchao ZhuLi HuPan PanYi YangPublished in: CVPR (2022)
Keyphrases
- multimodal interfaces
- hand movements
- speech recognition
- speech signal
- natural language
- sign language
- semantic network
- semantic annotation
- content based video retrieval
- hidden markov models
- multi modal
- generation process
- broadcast news
- high level
- semantic information
- multi stream
- spoken language
- semantic description
- language acquisition
- natural language understanding
- semantic relationships
- semantic web
- audio visual
- human computer interaction