I am a PhD student at the College of Computer Science and Technology, Zhejiang University (浙江大学计算机学院).
I am now working on the Audio Research Team at Zhejiang University, under the supervision of Prof. Zhou Zhao (赵洲). My current research focuses on multi-task music large language model with style control and spatial audio generation.
I graduated from Chu Kochen Honors College, Zhejiang University (浙江大学竺可桢学院), with dual bachelor’s degrees in Computer Science and Automation.
I also worked as a visiting scholar at University of Massachusetts Amherst, collaborating with Prof. Przemyslaw Grabowicz.
My research interests include Singing Voice Synthesis, Music Generation, Audio Generation, and other topics related to Natural Language Processing. I have published first-author papers at top international AI conferences, including NeurIPS, AAAI, and EMNLP.
I am actively seeking postdoctoral positions and research collaborations. Please feel free to contact me via email at yuzhang34@zju.edu.cn.
🔥 News
- 2024.11: We released the code of TCSinger (Zero-Shot Singing Voice Synthesis with Style Transfer and Multi-Level Style Control)!
- 2024.09: We released the full dataset of GTSinger (A Global Multi-Technique Singing Corpus for all singing tasks)!
- 2024.09: 🎉 1 paper is accepted by NeurIPS 2024 (Spotlight)!
- 2024.09: 🎉 1 paper is accepted by EMNLP 2024!
- 2024.06: We released the code of GTSinger (A Global Multi-Technique Singing Corpus for all singing tasks)!
- 2024.05: 🎉 1 paper is accepted by ACL 2024!
- 2024.05: We released the code of StyleSinger (Style Transfer for Out-of-Domain Singing Voice Synthesis)!
- 2023.12: 🎉 1 paper is accepted by AAAI 2024!
📝 Publications
🎙 Singing Voice Synthesis
GTSinger: A Global Multi-Technique Singing Corpus with Realistic Music Scores for All Singing Tasks
Yu Zhang, Changhao Pan, Wenxinag Guo, et al.
Project | 
- GTSinger is a large Global, multi-Technique, free-to-use, high-quality singing corpus with realistic music scores, designed for all singing tasks.
- Our work is promoted by multiple media and forums, such as
, and
.
StyleSinger: Style Transfer for Out-of-Domain Singing Voice Synthesis
Yu Zhang, Rongjie Huang, Ruiqi Li, et al.
Project |
- StyleSinger is the first singing voice synthesis model for zero-shot style transfer of out-of-domain reference singing voice samples.
TCSinger: Zero-Shot Singing Voice Synthesis with Style Transfer and Multi-Level Style Control
Yu Zhang, Ziyue Jiang, Ruiqi Li, et al.
Project |
- TCSinger is the first zero-shot SVS model for style transfer across cross-lingual speech and singing styles, along with multi-level style control.
ACL 2024Robust Singing Voice Transcription Serves Synthesis, Ruiqi Li, Yu Zhang, Yongqi Wang, et al.
🎼 Music Generation
🎖 Honors and Awards
- 2019.09 First-Class Academic Scholarship of Zhejiang University (Undergraduate) (Top 5%)
📖 Educations
- 2020.09 - 2025.06 (Expected), PhD, Computer Science, College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang
- 2016.09 - 2020.06, Undergraduate, Computer Science & Automation, Chu Kochen Honors College, Zhejiang University, Hangzhou, Zhejiang
💻 Research and Internships
- 2019.07-2020.01 Visiting Scholar at University of Massachusetts Amherst, working with Prof. Przemyslaw Grabowicz.
- 2018.09-2019.06 Research Assistant at Institute of Cyber-Systems and Control in Zhejiang University, working with Prof. Chunlin Zhou.