Research

I am a PhD student in Computer Science at Princeton University, advised by Dr. Adam Finkelstein. My long-term research goal is to build conversational artificial intelligence agents spanning modalities like speech and language. Most of my current research has focused on audio perception and machine learning, to that end designing perceptual objective metrics for evaluating audio quality. I co-organized HEAR 2021: A NeurIPS Challenge where the focus is on learning general purpose audio representations. My work was one of the best paper finalists at Interspeech 2020, and in the past, I have been a recipient of SN BOSE fellowship and the Indian Academy of Sciences summer research fellowship. As a research intern, I have spent time at Reality Labs Research Audio (Meta) and Adobe Research.