Combining unidirectional long short-term memory with convolutional output layer for high-performance speech synthesis.
Wenfu WangBo XuPublished in: ICASSP (2017)
Keyphrases
- speech synthesis
- speech recognition
- hidden layer
- recurrent neural networks
- text to speech
- output layer
- vocal tract
- feedforward neural networks
- feed forward
- neural network
- pattern recognition
- artificial intelligence
- radial basis function
- training data
- feature vectors
- rbf neural network
- artificial neural networks
- rbf network
- multi layer perceptron
- expert systems
- genetic algorithm