BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis.
Max W. Y. LamJun WangDan SuDong YuPublished in: CoRR (2022)
Keyphrases
- speech synthesis
- diffusion models
- denoising
- high quality
- speech recognition
- diffusion model
- text to speech
- information diffusion
- social networks
- image denoising
- vocal tract
- noisy images
- natural images
- image processing
- prosodic features
- influence maximization
- high resolution
- viral marketing
- pattern recognition
- multiscale
- machine learning
- neural network