Adversarial Training of Denoising Diffusion Model Using Dual Discriminators for High-Fidelity Multi-Speaker TTS.
Myeongjin KoYong-Hoon ChoiPublished in: CoRR (2023)
Keyphrases
- high fidelity
- diffusion model
- denoising
- image denoising
- anisotropic diffusion
- information diffusion
- real time
- diffusion models
- image processing
- high resolution
- text to speech
- high quality
- medical image compression
- diffusion process
- natural images
- partial differential equations
- social networks
- diffusion tensor
- online learning
- prosodic features
- laplace transform
- audio visual
- multiresolution
- speaker verification
- computational complexity
- image segmentation