Discrete Diffusion for Co-Speech Gesture Synthesis.
Ankur ChemburkarShuhong LuAndrew FengPublished in: ICMI Companion (2023)
Keyphrases
- multimodal interfaces
- hand movements
- diffusion process
- speech recognition
- gesture recognition
- hand gestures
- speech signal
- speech synthesis
- human computer interaction
- multi stream
- text to speech
- multiscale
- facial animation
- continuous stream
- image sequences
- diffusion processes
- diffusion equation
- continuous variables
- texture synthesis
- anisotropic diffusion
- hand gesture recognition
- learning mechanism
- audio visual
- language model
- hidden markov models
- user interface