
VITS 语音合成完全端到端TTS的里程碑
Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech(ICML 2021)KAIST概览:提出一种TTS模型框架VITS,用到normalizing flow和对抗训练方法,提高合成语音自然度,其中论文结果上显示已经和GT相当。代码:https://github.com/jaywalnut310/vitsDemo地址:https://jaywalnut310...



