Presently, I am investigating statistical models of speech signals and natural sounds using supervised and unsupervised learning algorithms. This work is largely incorporated into the DIRAC project ("Detection and Identification of Rare Auido-visual Cues") which started in January 2006.

During my Post-Doc, I worked on modeling dynamics of biomedical signal by complex ICA, see

J. Anemüller, T. J. Sejnowski, and S. Makeig. Complex independent component analysis of frequency-domain electroencephalographic data. Neural Networks, 16:1311-1323, 2003.
[ pdf | journal ]

J. Anemüer, J.-R. Duann, T. J. Sejnowski and S. Makeig. Spatio-temporal dynamics in fMRI recordings revealed with complex independent component analysis. Neurocomputing, 69:1502-1512, 2006.
[ pdf | journal ]

During my Ph.D., I was working on convolutive blind source separation of acoustic signals. Most of this work, including demos, is described on my old (now unmaintained) webpages in Oldenburg:

Infos and demos for blind separation of acoustic signals.