ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speech.
Rongjie HuangZhou ZhaoHuadai LiuJinglin LiuChenye CuiYi RenPublished in: CoRR (2022)
Keyphrases
- diffusion model
- text to speech
- high quality
- speech synthesis
- information diffusion
- anisotropic diffusion
- diffusion models
- prosodic features
- programming tool
- influence maximization
- diffusion tensor
- word processing
- text to speech synthesis
- diffusion process
- laplace transform
- high resolution
- social networks
- multiresolution
- image analysis
- multiscale
- information flow
- high order
- image quality