DiffSVC: A Diffusion Probabilistic Model for Singing Voice Conversion.
Songxiang LiuYuewen CaoDan SuHelen MengPublished in: ASRU (2021)
Keyphrases
- probabilistic model
- language model
- generative model
- diffusion process
- bayesian networks
- anisotropic diffusion
- expectation maximization
- data conversion
- music information retrieval
- diffusion model
- diffusion processes
- database
- information retrieval systems
- information retrieval
- emotion recognition
- tensor field
- text to speech