Publications

LEMAS: A 150K-Hour Large-scale Extensible Multilingual Audio Suite with Generative Speech Models

Zhiyuan Zhao, Lijian Lin, Ye Zhu, Kai Xie, Yunfei Liu, Yu Li

arXiv

paper / project

MelTok: 2D Tokenization for Single-Codebook Audio Compression

Jingyi Li*, Zhiyuan Zhao*, Zhisheng Zhang, Yunfei Liu, Lijian Lin, Ye Zhu, Jiahao Wu, Qiuqiang Kong, Yu Li

arXiv

paper

STFTCodec: High-Fidelity Audio Compression through Time-Frequency Domain Representation

Tao Feng*, Zhiyuan Zhao*, Yifan Xie, Yuqi Ye, Xiangyang Luo, Xun Guan, Yu Li

IEEE ICME, 2025

paper

Improving Model Stability and Training Efficiency in Fast Speed High Quality Expressive Voice Conversion System

Zhiyuan Zhao, Jingjun Liang, Zehong Zheng, Linhuang Yan, Zhiyong Yang, Wan Ding, Dongyan Huang

ACM ICMI, 2021

paper / demo