A real-time speech driven talking avatar based on deep neural network.
Kai ZhaoZhiyong WuLianhong CaiPublished in: APSIPA (2013)
Keyphrases
- real time
- neural network
- facial animation
- neural network model
- speech recognition
- speech signal
- back propagation
- neural nets
- data driven
- feed forward
- low cost
- feed forward neural networks
- broadcast news
- control system
- recurrent neural networks
- network architecture
- facial expressions
- sign language
- automatic speech recognition
- language acquisition
- deep learning
- fermentation process