Kevin Wilson's Research Page

I wish computers could understand/interpret audio more accurately and more robustly.


Selected publications:

Kevin Wilson, Trevor Darrell, Learning a Precedence Effect-like Weighting Function for the Generalized Cross-Correlation Framework, IEEE Transactions on Speech and Audio Processing, 2006 (to appear).

Kevin Wilson, Learning the Precedence Effect: Initial Real-World Tests, IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, 2005. PDF

Kevin Wilson, Trevor Darrell, Improving Audio Source Localization by Learning the Precedence Effect, IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005. PDF

Neal Checka, Kevin Wilson, Michael Siracusa, Trevor Darrell, Multiple Person and Speaker Activity Tracking with a Particle Filter, International Conference on Acoustics, Speech, and Signal Processing, 2004. PDF

Michael Siracusa, Louis-Philippe Morency, Kevin Wilson, John Fisher, Trevor Darrell, A Multi-Modal Approach for Determining Speaker Location and Focus, International Conference on Multi-modal Interfaces, pp. 77--80, 2003. PDF