Arbitrary speaker conversion based on speaker space bases constructed by deep neural networks.
Tetsuya HashimotoDaisuke SaitoNobuaki MinematsuPublished in: APSIPA (2016)
Keyphrases
- neural network
- speaker verification
- speech recognition
- audio visual
- low dimensional
- speaker recognition
- pattern recognition
- search space
- speaker diarization
- automatic speech recognition
- fault diagnosis
- speaker dependent
- higher dimensional
- training process
- multi layer
- multilayer perceptron
- feed forward
- basis functions
- back propagation
- artificial neural networks