SpeechAct: Towards Generating Whole-body Motion from Speech.
Jinsong ZhangMinjie ZhuYuxiang ZhangYebin LiuKun LiPublished in: CoRR (2023)
Keyphrases
- humanoid robot
- motion estimation
- image sequences
- space time
- speech recognition
- motion model
- optical flow
- motion segmentation
- motion analysis
- human motion
- camera motion
- motion field
- moving objects
- motion patterns
- spatial and temporal
- motion compensation
- spatio temporal
- dynamic scenes
- motion detection
- motion tracking
- motion capture
- speech signal
- text to speech
- speaker recognition
- rigid motion
- motion planning
- hand gestures
- motion parameters
- computer vision
- feature points