Towards Streaming Speech-to-Avatar Synthesis.
Tejas S. PrabhunePeter WuBohan YuGopala Krishna AnumanchipalliPublished in: CoRR (2023)
Keyphrases
- facial animation
- facial expressions
- speech recognition
- human faces
- data streams
- real time
- speech synthesis
- virtual world
- speech signal
- recognition engine
- video streaming
- sign language
- temporal coherence
- streaming data
- stream processing
- program synthesis
- virtual reality
- audio visual
- neural network
- real time streaming
- multi stream
- text to speech
- endpoint detection
- motion capture data
- spoken language
- head motion
- noisy environments
- active appearance models
- probabilistic model
- data sets