Conditional Deep Hierarchical Variational Autoencoder for Voice Conversion.
Kei AkuzawaKotaro OnishiKeisuke TakiguchiKohki MametaniKoichiro MoriPublished in: CoRR (2021)
Keyphrases
- random field model
- image segmentation
- learning algorithm
- multiple layers
- restricted boltzmann machine
- coarse to fine
- conditional logic
- hierarchical structures
- emotion recognition
- hierarchical model
- variational methods
- real time
- hierarchical clustering
- optical flow
- computer vision
- machine learning
- neural network
- data sets