QS-TTS: A Semi-Supervised Text-to-Speech Framework

QS-TTS is a semi-supervised TTS framework based on VQ-S3RL to effectively utilize more unlabeled speech audio to improve TTS quality while reducing its requirements for supervised data.

Data and Resources

Cite this as

Haohan Guo, Jiawen Kang, Fenglong Xie, Yujia Xiao, Xixin Wu, Helen Meng (2024). Dataset: QS-TTS: A Semi-Supervised Text-to-Speech Framework. https://doi.org/10.57702/w1p4v02n

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2309.00126
Author Haohan Guo
More Authors
Jiawen Kang
Fenglong Xie
Yujia Xiao
Xixin Wu
Helen Meng
Homepage https://hhguo.github.io/DemoQSTTS/