Talking heads synthesis from audio with deep neural networks.
Taiki ShimbaRyuhei SakuraiHirotake YamazoeJoo-Ho LeePublished in: SII (2015)
Keyphrases
- cross modal
- neural network
- pattern recognition
- artificial neural networks
- program synthesis
- self organizing maps
- genetic algorithm
- fuzzy logic
- neural network model
- feed forward
- multi layer
- network architecture
- texture synthesis
- data sets
- video sequences
- multimedia
- back propagation
- neural nets
- fuzzy systems
- feedforward neural networks
- cellular neural networks