About
Soham is an Applied Scientist in the Speech and Language Group. His current research specializes in source separation, speech enhancement, and sound understanding. His research has been integrated into various Microsoft products, including Edge Video Dubbing (opens in new tab), Video Translation API (opens in new tab), and Outlook Scheduler (opens in new tab). Previously, he received his PhD in Electrical and Computer Engineering from Carnegie Mellon University. The topic of his PhD thesis was learning audio foundation models for reasoning. The research details are available on his website (opens in new tab).