Co-speech Gesture Generation with Variational Auto Encoder.
Shinichi KaKoichi ShinodaPublished in: MMM (3) (2024)
Keyphrases
- multimodal interfaces
- speech recognition
- image segmentation
- hand movements
- human computer interaction
- hidden markov models
- bit rate
- speech signal
- rate distortion
- gesture recognition
- speech synthesis
- multi stream
- natural human computer interaction
- low complexity
- sign language
- optical flow computation
- english text
- learning mechanism
- audio visual
- error control
- american sign language
- endpoint detection
- computer vision