Period VITS: Variational Inference with Explicit Pitch Modeling for End-To-End Emotional Speech Synthesis.
Yuma ShirahataRyuichi YamamotoEunwoo SongRyo TerashimaJae-Min KimKentaro TachibanaPublished in: ICASSP (2023)
Keyphrases
- end to end
- speech synthesis
- variational inference
- speech recognition
- bayesian inference
- congestion control
- text to speech
- probabilistic graphical models
- latent dirichlet allocation
- gaussian process
- topic models
- mixture model
- posterior distribution
- image processing
- motion vectors
- model selection
- hidden markov models