Articulatory Text-to-Speech Synthesis Using the Digital Waveguide Mesh Driven by a Deep Neural Network.
Amelia Jane GullyTakenori YoshimuraDamian T. MurphyKei HashimotoYoshihiko NankakuKeiichi TokudaPublished in: INTERSPEECH (2017)
Keyphrases
- text to speech synthesis
- neural network
- waveguide
- text to speech
- artificial neural networks
- neural network model
- speech recognition
- genetic algorithm
- neural network is trained
- speech synthesis
- fuzzy artmap
- d mesh
- fault diagnosis
- back propagation
- fuzzy logic
- learning vector quantization
- low complexity
- prediction model
- self organizing maps
- multi layer perceptron
- activation function
- digital media
- feed forward neural networks
- digital libraries
- high data rate
- pattern recognition
- three dimensional