Statistical Parametric Speech Synthesis Incorporating Generative Adversarial Networks.
Yuki SaitoShinnosuke TakamichiHiroshi SaruwatariPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2018)
Keyphrases
- speech synthesis
- speech recognition
- text to speech
- data driven
- vocal tract
- statistical analysis
- prosodic features
- complex networks
- social networks
- network design
- speech corpus
- data sets
- cellular networks
- generative model
- feature extraction
- unsupervised learning
- information theoretic
- network structure
- semi supervised
- hidden markov models
- small world
- network topologies
- prior knowledge
- multi agent
- computer vision
- neural network