Voice source modelling using deep neural networks for statistical parametric speech synthesis.
Tuomo RaitioHeng LuJohn KaneAntti SuniMartti VainioSimon KingPaavo AlkuPublished in: EUSIPCO (2014)
Keyphrases
- speech synthesis
- text to speech
- neural network
- speech recognition
- prosodic features
- pattern recognition
- vocal tract
- statistical analysis
- data driven
- kernel density estimators
- fuzzy logic
- artificial neural networks
- hidden markov models
- genetic algorithm
- statistical information
- multilayer perceptron
- feed forward
- statistical inference
- deep learning
- fuzzy cognitive maps
- feature extraction
- information retrieval
- information theoretic
- statistical methods
- neural network model
- statistical models
- fault diagnosis
- statistical approaches
- training data
- back propagation
- nonlinear dynamic systems
- data sets