Saurjya Sarkar

I am a Research Scientist specializing in AI applications for Audio Processing and Music Information Retrieval with experience in developing commercial audio products and securing international and US patents. My work has been focused on driving innovative interdisciplinary research, and high-resource deep learning deployment, including projects highlighted by the Alan Turing Institute.

I completed my PhD in 2023 at the Centre for Digital Music, Queen Mary University of London on “Time-domain Music Source Separation for Choirs and Chamber Ensembles”. My research received the Best Student Paper Award at IEEE WASPAA 2023. After my PhD I was a Postdoctoral Researcher collaborating with a couple of Music Tech startups on an Innovate UK project using Source Separation for Vocalist Identification, Lyrics Transcription and Sample Detection. In April 2025, I joined UMG at Abbey Road Studios as an Audio ML Engineer.

Previously, I have developed VST plugins for cross-adaptive audio effects for live music using Csound at the Centre for Digital Music, Queen Mary University of London. I’ve also worked for Qualcomm on Audio Quality Testing Automation by developing audio analysis algorithms to quantify system level audio performance using perceptual metrics. I had a brief stint with Observational Astrophysics research at NCU Taiwan, which was an amazing experience including a residency at their Lulin Observatory.