Multi-Speaker and Multi-Domain Emotional Voice Conversion Using Factorized Hierarchical Variational Autoencoder.
Mohamed ElgaarJungbae ParkSang Wan LeePublished in: ICASSP (2020)
Keyphrases
- multi domain
- emotion recognition
- cross domain
- search computing
- domain specific
- speaker verification
- spoken dialogue systems
- heterogeneous networks
- synthesized speech
- prosodic features
- role based access control
- audio visual
- knowledge discovery
- contextual information
- prior knowledge
- restricted boltzmann machine
- machine learning
- neural network
- data sets