In July, 2003, I finished my Ph.D. in the department of Electrical and Computer Engineering at Carnegie Mellon University. I was a research assistant in the Robust Speech Recognition group, led by my advisor, Professor Richard Stern. My dissertation research focused on improving recognition accuracy in hands-free environments using microphone arrays. Specifically, I designed algorithms which incorporate information from the speech recognizer into the array processing stage in order to optimize the resulting speech recognition features, rather than the output waveform. A copy of my thesis is available on my Publications page. While at CMU, I was funded by a Graduate Research Fellowship from Microsoft Research.

Prior to working with microphone arrays, I did research on mask estimation for "missing feature" noise-compensation methods. Mask estimation involves blindly identifying those regions of spectrographic displays of speech that have been severely corrupted by noise. My approach, which resulted in my Master's thesis (2000), was to design a Bayesian classifier to estimate the likelihood that each time-frequency region was corrupt or not.

From 1996-1998, I worked at Teradyne, Inc. as an Applications Engineer. Teradyne makes automatic test equipment (ATE) for the semiconductor industry. My group focused on developing test solutions for mixed-signal telecommunications and intelligent power IC's.

I did my undergraduate work at Brown University, in Providence, RI, graduating in 1996. I worked in the Laboratory for Engineering Man/Machine Systems (LEMS) with Professor Harvey Silverman on a huge microphone array project that was called, in fact, the Huge Microphone Array.

I am currently a Researcher in the Speech Technology Group at Microsoft Research, in Redmond, WA.