ConvoFusion: Multi-Modal Conversational Diffusion for Co-Speech Gesture Synthesis.
Muhammad Hamza MughalRishabh DabralIkhsanul HabibieLucia DonatelliMarc HabermannChristian TheobaltPublished in: CoRR (2024)
Keyphrases
- multi modal
- audio visual
- multimodal interfaces
- hand movements
- speech recognition
- gesture recognition
- human computer interaction
- hidden markov models
- anisotropic diffusion
- multi modality
- high dimensional
- diffusion process
- human communication
- speech signal
- semantic concepts
- automatic speech recognition
- spoken language
- hand gestures
- nonlinear diffusion
- image annotation
- conversational speech
- uni modal
- video search
- high level
- broadcast news