I'm an Applied Scientist on the Microsoft Speech team, working on speech and audio processing.
My work focuses on building audio processing technology to reduce communication barriers. This ranges from front-end audio processing like speech enhancement to building general purpose audio assistants. My research gets deployed in products like Teams, Edge, Outlook.
Previously, I received my masters degree from Carnegie Mellon University, MLSP Group and advised by Bhiksha Raj. I completed my B.Tech from VJTI, working on NLP.
Recent works: Video Translation, Pengi, CLAP
Links: Google Scholar • GitHub • Twitter • LinkedIn