Shitong Xu

PhD candidate, University of Oxford

I am a fourth-year PhD candidate in Department of Computer Science at the University of Oxford, supervised by Prof. Niki Trigoni and Prof. Andrew Markham. I obtained my Master and Bachlor degree in Imperial College London, where I completed my Master thesis under the supervision of Prof. Ben Glocker.

Research Interests

My research lies at the intersection of Audio Signal Processing and Multimodal Machine Learning, with a focus on understanding the semantic and spatial properties of complex acoustic environments.

My research spans three interconnected directions:

• Semantic Audio Understanding: Robust speech and audio analysis in complex acoustic environments, including target speaker extraction and pathological speech detection.
• Spatial Audio Modeling: Sound source localization, spatially conditioned extraction, and spatial audio rendering under diverse acoustic and microphone configurations.
• Spatial-Semantic Scene Understanding: Integrating semantic and spatial information for higher-level acoustic scene understanding, including spatial audio question answering.

More broadly, I have deep interest in the following fields:

• Physics-Informed Machine Learning
• Electroencephalography (EEG) Brain Signal Processing