I’m a first-year Ph.D. student at the Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), supervised by Professor Zhizheng Wu.

I graduated from University of Electronic Science and Technology of China(电子科技大学) with a bachelor’s degree and from the Department of Electronic and Computer Engineering, Peking University (北京大学信息工程学院) with a master’s degree, advised by Yuexian Zou (邹月娴).

My research interest includes voice security, spoken keyword spotting and speaker verification. I have published 4 papers at the top international conferences such as ICASSP, INTERSPEECH.

🔥 News

  • 2023.12: Two papers are accepted by ICASSP 2024!

📝 Publications

📚 Attack and Defense of Speaker Verification

ICASSP 2024
sym

AdvSV: An Over-the-Air Adversarial Attack Dataset for Speaker Verification
Li Wang, Jiaqi Li, Yuhao Luo, Jiahao Zheng, Lei Wang, Hao Li, Ke Xu, Chengfang Fang, Jie Shi, Zhizheng Wu

  • Deep neural networks, including Automatic Speaker Verification (ASV) systems, are vulnerable to adversarial attacks. This study introduces an open-source adversarial attack dataset, AdvSV, for ASV research, focusing initially on over-the-air attacks, which involve perturbation generation, loudspeakers, microphones, and varying acoustic environments. Based on the Voxceleb1 Verification test set, AdvSV simulates over-the-air attacks using representative ASV models, aiming to standardize and facilitate reproducible research in this field.
ICASSP 2024
sym

An Initial Investigation of Neural Replay Simulator for Over-the-Air Adversarial Perturbations to Automatic Speaker Verification
Jiaqi Li, Li Wang, Liumeng Xue, Lei Wang, Zhizheng Wu

  • Deep Learning has advanced Automatic Speaker Verification (ASV), but physical access adversarial attacks, particularly over-the-air involving loudspeakers, microphones, and replaying environments, are less studied. This research explores using a neural replay simulator to enhance over-the-air attack robustness in ASV. By simulating the replay process with a neural waveform synthesizer, the study on the ASVspoof2019 dataset shows increased success rates of these attacks, highlighting security concerns for ASV in physical access scenarios.

📚 Speaker Verification and Keyword Spotting Multi-task

ICASSP 2022
sym

Learning Decoupling Features Through Orthogonality Regularization
Li Wang, Rongzhi Gu, Weiji Zhuang, Peng Gao, Yujun Wang, Yuexian Zou

  • This paper is committed to improving the model performance of personalized keyword spotting (identifying keywords and speakers) tasks. This paper believes that the key of personalized keyword spotting task is how to effectively extract the features shared by two tasks and decouple the features related to tasks. This paper creatively uses orthogonal regularization to constrain the model to decouple keyword information and speaker information.

🎙 Spoken Keyword Spotting

INTERSPEECH 2021
sym

Text Anchor Based Metric Learning for Small-Footprint Keyword Spotting
Li Wang, Rongzhi Gu, Nuo Chen, Yuexian Zou

  • Innovatively propose a measurement learning method based on text anchor, and use BERT to generate embedding with rich semantic information, so that the model can understand the semantic information of keywords.

📖 Educations

  • 2023.06 - Present, Ph.D., The Chinese University of Hong Kong, Shenzhen, Shenzhen.
  • 2019.06 - 2022.07, Master, Peking University, Shenzhen.
  • 2015.09 - 2019.06, Undergraduate, University of Electronic Science and Technology of China, Chengdu.

💻 Internships

🏀 Services

👏 Template of This Page

Thanks to Yi Ren (任意) for his open source contribution, template link AcadHomepage .