This page aims to collect Opencpop-related publications.

1. WeSinger: Data-augmented Singing Voice Synthesis with Auxiliary Losses. pdf

2. SingAug: Data Augmentation for Singing Voice Synthesis with Cycle-consistent Training Strategy. pdf

3. Learn2Sing 2.0: Diffusion and Mutual Information-Based Target Speaker SVS by Learning from Singing Teacher. pdf

4. Muskits: an End-to-End Music Processing Toolkit for Singing Voice Synthesis. pdf

Sponsor Link
1. Fuxi AI Lab, NetEase Inc., Hangzhou, China. link
2. School of Pop Music & Dance, Shanghai Institute of Visual Arts, China. link
3. College of Design and Innovation of Tongji University, China. link
4. Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi’an, China. link
5. Wenet-E2E community, China. link
6. TianYin, NetEase Inc., Hangzhou, China. link
7. XiYin, NetEase Inc., Hangzhou, China. link



  • Thanks to Changjie Fan, Tangjie Lv, Le Li, Lin Jiang and Fuxi’s colleagues for their support to opencpop project.
  • Thanks to Mingming Fu, Tianyao Bai, Chen Li, Yangfan Xu, Yuxia Wu, Yi Xiang, Cheng Zeng and other colleagues in the audio department of Leihuo for their guidance and support in music basics.
  • Thanks to Xiangyu Zhao, Peng Li, Yang Bai, Xiaojing Liang and other cloud music colleagues for their long-term communication and support in the field of AI music.
  • Thanks to those who quietly devote themselves to the cause of music.