About me
I am a postdoctoral researcher and Shuimu Scholar at Tsinghua Shenzhen International Graduate School (SIGS), Shenzhen, China. I received my Ph.D. in Electrical and Computer Engineering from Toronto Metropolitan University in 2025, where I was fortunate to work with Prof. Xiao-Ping (Steven) Zhang and Prof. Lian Zhao. Prior to that, I received my B.A.Sc. from the University of Toronto and my M.Eng. from Toronto Metropolitan University in 2019 and 2021, respectively.
My research focuses on multimedia processing and trustworthy multimedia AI, particularly speech deepfake detection. My long-term goal is to develop robust and interpretable systems that can reliably detect and understand manipulated multimedia content in real-world scenarios. My current research spans generalizable deepfake detection, partial manipulation detection, interpretability, and multimodal learning.
My work has appeared in venues including IEEE Signal Processing Letters, Interspeech, IEEE WASPAA, and IEEE ICME. I am also actively involved in the multimedia and signal processing communities through conference organization, tutorials, reviewing, and professional service.
Recent News
[2026/09] One paper is accepted by IEEE SLT 2026.
[2026/08] We organized a special session at ACM Multimedia Asia 2026 on Trustworthy Speech and Audio AI (Submission Deadline: August 21, 2026).
[2026/07] I will give a talk at the Trustworthy Audio Processing Methods for Generative Audio Special Session at NCMMSC 2026, titled Deepfake Speech Detection Based on Authentic and Fake Speech Difference Modeling.
[2026/06] I am serving as Financial Co-Chair of the IEEE IVMSP Workshop 2026. Welcome to Shenzhen!
[2025/12] Our paper on Partial Deepfake Speech Dataset is accepted by IEEE ICME 2026 as a Spotlight paper!
[2025/10] I joined Tsinghua Shenzhen International Graduate School as a Postdoctoral Researcher and Shuimu Scholar!
[2025/10] I received my Ph.D. in Electrical and Computer Engineering from Toronto Metropolitan University!
[2025/08] We presented our tutorial on Multimedia Deepfake Detection at IEEE AVSS 2025.
[2025/07] I successfully defended my PhD! Dissertation title: Deepfake Speech Detection: A Focus on Generalization through Spectral-Temporal Domain Learning.
[2025/07] Our paper on Partial Deepfake Speech Detection was published in IEEE Signal Processing Letters [PDF]!
[2025/02] Our survey paper on Speech Deepfake Detection was published in ACM Computing Surveys!
[2024/09] I presented our paper at Interspeech 2024 oral session.
[2024/07] I have successfully passed my PhD candidacy exam on “DEEPFAKE AUDIO DETECTION: A Foucs on Efficiency, Robustness and Interpretability”!
[2024/07] We presented our tutorial on Multimedia Deepfake Detection at ICME 2024.
[2024/05] Awarded the Ontario Graduate Scholarship (OGS) for the second consecutive year (one of four international student recipients at TMU).
[2024/03] I participated TMU Three-Minute Thesis (3MT®) Competition. [Youtube]
[2023/10] I attended IEEE WASPAA to present our work. [poster]