Reducing over-smoothness in speech synthesis using Generative Adversarial Networks.
Leyuan ShengEvgeniy N. PavlovskiyPublished in: CoRR (2018)
Keyphrases
- speech synthesis
- speech recognition
- text to speech
- vocal tract
- social networks
- network model
- complex systems
- unsupervised learning
- prosodic features
- data sets
- data driven
- neural network
- generative model
- network analysis
- hidden markov models
- cost function
- language model
- network structure
- heterogeneous networks
- multi agent
- information retrieval