Zero-Shot TTS

Speaking from Coarse to Fine: Improving Neural Codec Language Model via Multi-Scale Speech Coding and Generation
Conference paper accepted by IEEE ICASSP 2025.
Haohan Guo, Fenglong Xie, Dongchao Yang, Xixin Wu, Helen Meng
PDF Cite Project
FireRedTTS: A Foundation Text-To-Speech Framework for Industry-Level Generative Speech Applications
Preprint: an industry-level foundation TTS framework.
Hao-Han Guo, Yao Hu, Kun Liu, Fei-Yu Shen, Xu Tang, Yi-Chen Wu, Feng-Long Xie, Kun Xie, Kai-Tuo Xu
PDF Cite Code Project