Adaptation of an Expressive Single Speaker Deep Neural Network Speech Synthesis System.
Jonathan ParkerYannis StylianouRoberto CipollaPublished in: ICASSP (2018)
Keyphrases
- speech synthesis
- speech recognition
- neural network
- prosodic features
- vocal tract
- speaker adaptation
- text to speech
- hidden markov models
- artificial neural networks
- self organizing maps
- training algorithm
- automatic speech recognition
- multi layer
- back propagation
- speech signal
- network architecture
- feed forward neural networks
- probabilistic neural network
- training process
- expert systems
- multimedia