Trajectory training considering global variance for speech synthesis based on neural networks.
Kei HashimotoKeiichiro OuraYoshihiko NankakuKeiichi TokudaPublished in: ICASSP (2016)
Keyphrases
- speech synthesis
- neural network
- training process
- speech recognition
- training algorithm
- text to speech
- feedforward neural networks
- multi layer perceptron
- feed forward neural networks
- backpropagation algorithm
- neural network training
- pattern recognition
- back propagation
- vocal tract
- prosodic features
- supervised learning
- neural network model
- artificial neural networks
- genetic algorithm
- radial basis function network
- training phase
- multilayer perceptron
- feed forward
- neural network structure
- self organizing maps
- error back propagation
- recurrent networks
- speech corpus
- intra class
- fuzzy neural network
- hidden layer
- multi layer
- standard deviation
- recurrent neural networks
- image coding
- training examples
- training samples
- hidden markov models