Towards Variable and Coordinated Holistic Co-Speech Motion Generation.
Yifei LiuQiong CaoYandong WenHuaiguang JiangChangxing DingPublished in: CoRR (2024)
Keyphrases
- space time
- human motion
- optical flow
- image sequences
- motion estimation
- motion detection
- speech recognition
- motion model
- motion analysis
- motion capture
- speech signal
- multi agent
- reference frame
- motion parameters
- motion segmentation
- camera motion
- motion field
- facial motion
- speech synthesis
- text to speech
- emotion recognition
- image motion
- moving objects
- visual data
- spatio temporal
- automatic speech recognition
- visual perception
- mobile robot
- audio visual
- motion planning
- recognition engine
- feature points