Diff-TTSG: Denoising probabilistic integrated speech and gesture synthesis.
Shivam MehtaSiyang WangSimon AlexandersonJonas BeskowÉva SzékelyGustav Eje HenterPublished in: CoRR (2023)
Keyphrases
- denoising
- image denoising
- multimodal interfaces
- speech recognition
- gesture recognition
- hand movements
- noisy images
- natural images
- total variation
- wavelet domain
- program synthesis
- probabilistic model
- bayesian networks
- denoising algorithm
- sign language
- wavelet packet
- noise removal
- human computer interaction
- probabilistic logic
- text to speech
- generative model
- image processing
- gaussian noise
- hand gestures
- pattern recognition
- multi stream
- speech synthesis
- speech signal