Boosting Fast and High-Quality Speech Synthesis with Linear Diffusion.

Haogeng Liu Tao Wang Jie Cao Ran He Jianhua Tao

Published in: CoRR (2023)

Keyphrases

speech synthesis
high quality
speech recognition
text to speech
vocal tract
prosodic features
image quality
low quality
base classifiers
speech corpus
ensemble learning
closed form
neural network
linear systems
diffusion model
language model
medical images
ground truth
information retrieval
machine learning