I’m currently a research scientist as Johns Hopkins University, focusing on speech and audio technology. In particular, my work frequently falls under the challenges of “cocktail party problem,” i.e. being able to process speech in an environment with lots of people, sometimes talking at the same time, with background noise or music. Specifically, I focus on speech enhancement and separation (removing interfering speech or noise) and on speaker diarization (labeling “who spoke when”).

My technical background is in signal processing, statistical modeling, and deep learning. I received my PhD and MS in Electrical & Computer Engineering at Johns Hopkins University in the Center for Language and Speech Processing, co-advised by Sanjeev Khudanpur and Shinji Watanabe. Before that, I received my BS from Carnegie Mellon University. After spending a few years as a Research Scientist on Amazon’s acoustic event detection team, I returned to Hopkins as a research scientist.