HeyangXue1997

icon company Kunlun icon location Beijing icon location Speech synthesis/Singing voice synthesis/Machine learning,Beijing, China

Results 4 repositories owned by HeyangXue1997

Learn2Sing2.0

178
Stars
26
Forks
Watchers

Diffusion and Mutual Information-Based Target Speaker SVS by Learning from Singing Teacher

verified publisher icon WelkinYang

GradTTS

190
Stars
19
Forks
Watchers

Pytorch implementation of "Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech"

verified publisher icon WelkinYang

EMPHASIS-pytorch

15
Stars
3
Forks
Watchers

EMPHASIS: An Emotional Phoneme-based Acoustic Model for Speech Synthesis System

verified publisher icon WelkinYang

WaveODE

60
Stars
7
Forks
Watchers

An ODE-based generative neural vocoder using Rectified Flow

verified publisher icon WelkinYang