Waveform Generation for Text-to-speech Synthesis Using Pitch-synchronous Multi-scale Generative Adversarial Networks.
Lauri JuvelaBajibabu BollepalliJunichi YamagishiPaavo AlkuPublished in: ICASSP (2019)
Keyphrases
- multiscale
- text to speech synthesis
- generative model
- neural network
- multiple scales
- social networks
- text to speech
- scale space
- natural images
- image representation
- generation process
- data sets
- image processing
- computer networks
- network structure
- discriminative learning
- network model
- network analysis
- image segmentation
- data driven
- peer to peer
- object detection
- multi agent