About me

Welcome! I am currently pursuing a PhD at Centre for Digital Music (C4DM), Queen Mary University of London under the supervision of Professor Simon Colton. My research is focused on neuro-symbolic approaches for generating music.

Prior to QMUL, I was also part of the Interactive Audio Lab at Northwestern headed by Professor Bryan Pardo.

I am passionate about deep learning applications in music both in the symbolic and raw audio domains along with audio signal processing techniques for speech modeling. I am a co-author of VoiceBlock, an adversarial audio to audio model for de-identification of speakers which was recently published in NeurIPS’ 22. I have also received a Microsoft grant for a research project on bird sound recognition which I presented at ICEI’ 2020+1 hosted by Digital University, Kerala.

My professional experience includes working with companies such as Boston Consulting Group (BCG) and Epsilon where I was senior data scientist. My work here was in the ML product engineering team and I was responsible for building and deploying recommendation systems and predictive modeling solutions as a product for retail and FMCG clients.