FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis.

Rongjie Huang Max W. Y. Lam Jun Wang Dan Su Dong Yu Yi Ren Zhou Zhao

Published in: IJCAI (2022)

Keyphrases

diffusion model
speech synthesis
high quality
speech recognition
text to speech
vocal tract
diffusion models
information diffusion
prosodic features
anisotropic diffusion
diffusion process
laplace transform
decision making
machine learning
image quality