Michael Richard Siracusa

I am a graduate student working with John Fisher and Alan Willsky in the Computer Science and Artificial Intelligence Laboratory at MIT. At some point I will make this page a little more exciting. I have avoided making a web page for years, but I guess I need to just give up and make one before I graduate.

Some Recent Publications

M. R. Siracusa and J. W. Fisher III, "Dynamic Dependency Tests: Analysis and Applications to Multi-modal Data Association" AIStats 2007.

M. R. Siracusa and J. W. Fisher III, "Inferring Dynamic Dependency with Applications to Link Analysis," Asilomar Conference on Signals, Systems, and Computers, 2006.

Some Less Recent Publications

M.R. Siracusa and J.W. Fisher III. "Modeling and estimating dynamic dependency structure: Applications to audio-visual speaker labeling". In Yann LeCun and Yoshua Bengio, editors, Proceedings of the Learning Workshop, Snowbird, Utah, Apr 2006.

M.R. Siracusa, K. Tieu, A. Ihler, J. Fisher III, and A.S Willsky, "Estimating dependency and significance for high-dimensional data", ICASSP 2005.

K. Saenko, K. Livescu, M. Siracusa, K. Wilson, J. Glass, T. Darrell, "Visual Speech Recognition with Loosely Synchronized Feature Streams", ICCV 2005.

N. Checka, K. Wilson, M. Siracusa, T. Darrell, "Multiple Person and Speaker Activity Tracking with a Particle Filter", ICASSP 2004.

M.R. Siracusa, L-P. Morency, K. Wilson, J. Fisher III and T. Darrell, "A Multi-Modal Approach for Determining Speaker Location and Focus", ICMI 2003

Masters

M. R. Siracusa, "Statistical Modeling and Analysis of Audio-Visual Association in Speech" MIT Institute Archives - Noncirculating Collection 3 | THESIS E.E. S.M. 2004

Data
For CUAVE and other AV Data used please go here.