Parallel and cascaded deep neural networks for text-to-speech synthesis.
Manuel Sam RibeiroOliver WattsJunichi YamagishiPublished in: SSW (2016)
Keyphrases
- text to speech synthesis
- neural network
- pattern recognition
- parallel processing
- neural nets
- fuzzy logic
- face detection
- genetic algorithm
- text to speech
- shared memory
- multilayer perceptron
- artificial intelligence
- feed forward
- fault diagnosis
- control system
- parallel computing
- activation function
- deep learning
- single layer
- image processing
- real time