On the training aspects of Deep Neural Network (DNN) for parametric TTS synthesis.
Yao QianYuchen FanWenping HuFrank K. SoongPublished in: ICASSP (2014)
Keyphrases
- training process
- neural network
- training algorithm
- feed forward neural networks
- multi layer perceptron
- back propagation
- feedforward neural networks
- neural network training
- backpropagation algorithm
- artificial neural networks
- deep architectures
- recurrent networks
- neural network model
- training set
- training data
- neural network structure
- training patterns
- text to speech
- pattern recognition
- network architecture
- train a neural network
- multi layer
- fuzzy artmap
- backpropagation neural network
- training speed
- texture synthesis
- program synthesis
- online learning
- supervised learning
- semi supervised
- hidden markov models
- genetic algorithm