Diff-TTS: A Denoising Diffusion Model for Text-to-Speech.
Myeonghun JeongHyeongju KimSung Jun CheonByoung Jin ChoiNam Soo KimPublished in: CoRR (2021)
Keyphrases
- text to speech
- diffusion model
- denoising
- image denoising
- speech synthesis
- anisotropic diffusion
- information diffusion
- diffusion models
- natural images
- diffusion process
- image processing
- prosodic features
- programming tool
- diffusion tensor
- text to speech synthesis
- word processing
- laplace transform
- writing skills
- magnetic resonance images
- information flow
- community detection
- high quality
- computer vision