Xu Gan
Xu Gan

AI Researcher

I am an audio AI researcher and engineer working at the intersection of generative audio, spatial audio, and real-time music applications. My recent work focuses on AI-assisted spatial audio production, on-device music generation and deployment, music wellness applications, sound effect design, and bringing audio models into practical product environments.Before my current role, I worked on speech synthesis, voice conversion, and end-to-end music generation, which shaped my broader interest in controllable, expressive, and deployable audio generation systems.

Experience

AI Researcher

Tencent Music Entertainment Group

Research on generative AI for audio, spatial audio, and audio effects.
Generative Audio Spatial Audio Audio Effects

AI Research Intern

BiliBili

Applied research on multimedia AI.

Education

M.S. in Computer Science

Fudan University

B.S. in Communication Engineering

Shanghai University