A Hybrid Temporal Modeling Phoneme Recognized Network for Real-Time Speech Animation.
Zixiao YuHaohong WangJian RenPublished in: MIPR (2020)
Keyphrases
- real time
- speech recognition
- speech synthesis
- low cost
- real time rendering
- spatio temporal
- automatic speech recognition
- automatic speech recognition systems
- facial animation
- network model
- temporal information
- computer graphics
- hidden markov models
- text to speech
- speech signal
- computer networks
- communication networks
- vision system
- affect sensing
- computer generated imagery
- temporal data
- temporal constraints
- human body
- peer to peer
- control system
- pattern recognition
- computer vision