Unified speech and gesture synthesis using flow matching.
Shivam MehtaRuibo TuSimon AlexandersonJonas BeskowÉva SzékelyGustav Eje HenterPublished in: CoRR (2023)
Keyphrases
- multimodal interfaces
- matching algorithm
- image matching
- speech recognition
- hidden markov models
- hand movements
- multi stream
- flow field
- audio visual
- flow patterns
- program synthesis
- texture synthesis
- pattern matching
- speech signal
- user interface
- hand gesture recognition
- matching process
- shape matching
- graph matching
- speech synthesis
- feature points
- recognition engine
- endpoint detection