Junan Zhang

Junan Zhang

Auto-generated profile, based on publicly available information

Junan Zhang

The Chinese University of Hong Kong, Shenzhen

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 April 2025 in ACM Transactions on Software Engineering and Methodology
Verified
Journal Article
Open access
JZJunan Zhang
Junan Zhang
KHKaifeng Huang
Kaifeng Huang
YHYiheng Huang
Yiheng Huang
BCBihuan Chen
Bihuan Chen
RWRuisi Wang
Ruisi Wang
XPXin Peng
Xin Peng
Open source software (OSS) supply chain enlarges the attack surface of a software system, which makes package registries attractive targets for attacks. Recently, multiple package registries have received intensified attacks with malicious packages. Of those package registries, NPM and PyPI are two of the most severe victims. Existing malicious package detectors are developed with features from a list of packages of the same ecosystem and deployed within the same ecosystem exclusively, which is infeasible to utilize the knowledge of a new malicious NPM package detected recently to detect the new malicious package in PyPI. Moreover, existing detectors lack support to model malicious behavior of OSS packages in a sequential way. To address the two limitations, we propose a single detection model using malicious behavior sequence, named Cerebro , to detect malicious packages in NPM and PyPI. We curate a feature set based on a high-level abstraction of malicious behavior to enable multi-lingual knowledge fusing. We organize extracted features into a behavior sequence to model sequential malicious behavior. We fine-tune the pre-trained language model to understand the semantics of malicious behavior. Extensive evaluation has demonstrated the effectiveness of Cerebro over the state-of-the-art as well as the practically acceptable efficiency. Cerebro has detected 683 and 799 new malicious packages in PyPI and NPM, and received 707 thank letters from the official PyPI and NPM teams.

25 July 2025 in IEEE Transactions on Audio, Speech and Language Processing
Verified
Journal Article
Closed access
JZJunan Zhang
Junan Zhang
JYJing Yang
Jing Yang
ZFZihao Fang
Zihao Fang
YWYuancheng Wang
Yuancheng Wang
ZZZehua Zhang
Zehua Zhang
ZWZhizheng Wu
Zhizheng Wu
We introduce AnyEnhance, a unified generative model for voice enhancement that processes both speech and singing voices. Based on a masked generative model, AnyEnhance is capable of handling both speech and singing voices, supporting a wide range of enhancement tasks including denoising, dereverberation, declipping, super-resolution, and target speaker extraction, all simultaneously and without fine-tuning. AnyEnhance introduces a prompt-guidance mechanism for in-context learning, which allows the model to natively accept a reference speaker’s timbre. In this way, it could boost enhancement performance when a reference audio is available and enable the target speaker extraction task without altering the underlying architecture. Moreover, we also introduce a self-critic mechanism into the generative process for masked generative models, yielding higher-quality outputs through iterative self-assessment and refinement. Extensive experiments on various enhancement tasks demonstrate AnyEnhance outperforms existing methods in terms of both objective metrics and subjective listening tests.

1 January 2026 in IEEE Transactions on Audio, Speech and Language Processing
Verified
Journal Article
Closed access
YGYicheng Gu
Yicheng Gu
JZJunan Zhang
Junan Zhang
CWChaoren Wang
Chaoren Wang
JLJerry Li
Jerry Li
ZWZhizheng Wu
Zhizheng Wu
LJLauri Juvela
Lauri Juvela

9 March 2026 in IEEE Transactions on Audio, Speech and Language Processing
Verified
Journal Article
Closed access
XZXueyao Zhang
Xueyao Zhang
JZJunan Zhang
Junan Zhang
YWYuancheng Wang
Yuancheng Wang
CWChaoren Wang
Chaoren Wang
YCYuanzhe Chen
Yuanzhe Chen
ZWZhizheng Wu
Zhizheng Wu
Controllable human voice generation, particularly for expressive domains like singing, remains a significant challenge. This paper introduces ${\bm {Vevo2}}$, a unified framework for controllable speech and singing voice generation. To tackle issues like the scarcity of annotated singing data and to enable flexible controllability, Vevo2 introduces two audio tokenizers: (1) a unified music-notation-free prosody tokenizer that captures prosody and melody from speech, singing, and even instrumental sounds, and (2) a unified content-style tokenizer that encodes linguistic content, prosody, and style for both speech and singing, while enabling timbre disentanglement. Vevo2 consists of an auto-regressive content-style modeling stage, which aims to enable controllability over text, prosody, and style, as well as a flow-matching acoustic modeling stage that allows for timbre control. Particularly, during the speech-singing joint training of the AR model, we propose both explicit and implicit prosody learning strategies to bridge speech and singing voice. Moreover, to further enhance the Vevo2's ability to follow text and prosody, we design a multi-objective post-training task that integrates both intelligibility and prosody similarity alignment. Experimental results show that the unified modeling in Vevo2 brings mutual benefits to both speech and singing voice generation. Additionally, Vevo2's effectiveness across a wide range of synthesis, conversion, and editing tasks for both speech and singing further demonstrates its strong generalization ability and versatility. Audio samples are are available at https://versasinger.github.io/.