About Me

Hi :D ! I’m a … Ph.D. student at The Chinese University of Hong Kong, Shenzhen, advised by Prof. Zhizheng Wu. I spent my undergraduate studies at Fudan University, majoring in software enginnering, with Prof. Bihuan Chen and Prof. Kaifeng Huang.

Beyond academia, I’m an amateur music producer with over 2 million plays on netease cloud music. In my free time, I enjoy playing rhythm games like osu! and watching slice-of-life (iyashikei) anime like miss kobayashi’s dragon maid (i like elma very much).

"鹈鹕" is a black & white british shorthair, ... old. He became my family member since November 2024, and has lived with me for ... days.

Research Interests

High-Quality and Controllable Music Generation:

High-Quality: speech/singing voice enhancement (de-noise, de-reverb, super-resolution, etc.), music restoration.
Controllable: speech/singing voice generation/editing, accompaniment generation, music-to-music generation.

Selected Publications

Full list at Google Scholar. *Equal Contribution.

Audio Enhancement:

TASLP

AnyEnhance: A Unified Generative Model with Prompt-Guidance and Self-Critic for Voice Enhancement

Junan Zhang, Jing Yang, Zihao Fang, Yuancheng Wang, Zehua Zhang, Zhuo Wang, Fan Fan, Zhizheng Wu

IEEE Transactions on Audio, Speech and Language Processing (TASLP), 2025.

PDF Code Website
Report

AnyEnhance2: Controlling Generative Freedom for Faithful and Universal Audio Restoration

Junan Zhang, Chong Jing, Jing Yang, Yingda Shen, Yuancheng Wang, Fan Fan, Zhizheng Wu

Technical Report, 2026.
AAAI

Multi-Metric Preference Alignment for Generative Speech Restoration

Junan Zhang, Xueyao Zhang, Jing Yang, Yuancheng Wang, Fan Fan, Zhizheng Wu

The 40th Annual AAAI Conference on Artificial Intelligence (AAAI), 2026.

PDF Website

Music Generation:

ICASSP

AnyAccomp: Generalizable Accompaniment Generation via Quantized Melodic Bottleneck

Junan Zhang*, Yunjia Zhang*, Xueyao Zhang, Zhizheng Wu

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2026.

PDF Code Website
NeurIPS

AnyEdit: A Unified Framework for Speech and Singing Voice Editing with Real-World Environmental Consistency

Yunjia Zhang*, Junan Zhang*, Jing Yang*, Xueyao Zhang, Fan Fan, Zhizheng Wu

Annual Conference on Neural Information Processing Systems (NeurIPS), 2026.

PDF Website
ISMIR

DDSynth-RL: Audio Synthesizer Inversion via Discrete Diffusion with Reinforcement Learning

Tristan Wu, Daniel Chin, Junan Zhang, Junyan Jiang, Yansen Jing, Gus Xia

International Society for Music Information Retrieval Conference (ISMIR), 2026.

PDF Best Paper Award Nominee
TASLP

Vevo2: Bridging Controllable Speech and Singing Voice Generation via Unified Prosody Learning

Xueyao Zhang, Junan Zhang, Yuancheng Wang, Chaoren Wang, Yuanzhe Chen, Dongya Jia, Zhuo Chen, Zhizheng Wu

IEEE Transactions on Audio, Speech and Language Processing (TASLP), 2026.

PDF Website

Misc:

SLT

Amphion: an Open-Source Audio, Music, and Speech Generation Toolkit

Xueyao Zhang*, Liumeng Xue*, Yicheng Gu*, Yuancheng Wang*, Jiaqi Li*, Haorui He, Chaoren Wang, Songting Liu, Xi Chen, Junan Zhang, Zihao Fang, Haopeng Chen, Tze Ying Tang, Lexiao Zou, Mingxuan Wang, Jun Han, Kai Chen, Haizhou Li, Zhizheng Wu

2024 IEEE Spoken Language Technology Workshop (SLT), 2024.

PDF Code
TOSEM

Killing two birds with one stone: Malicious package detection in NPM and PyPI using a single model of malicious behavior sequence

Junan Zhang, Kaifeng Huang, Yiheng Huang, Bihuan Chen, Ruisi Wang, Chong Wang, Xin Peng

ACM Transactions on Software Engineering and Methodology (TOSEM), 2025.

PDF my first academic paper :3