ICA 2007

ICA 2007
7th International Conference on
Independent Component Analysis
and Signal Separation

London, UK        9 - 12 September 2007

Banner showing images of London
- Home
- Committee
- Call for Papers
- Submission
- Info for Presenters
- Dates
- Programme
- Tutorials
- Keynotes
- Papers
- Registration
- Accommodation
- Venue
- Maps
- Arrival
- Travel Tips
- Links
- Contact


The keynote speakers at ICA 2007 will be:

Scott Makeig
Swartz Center for Computational Neuroscience, Institute for Neural Computation, UCSD, USA

Shoji Makino
NTT Communication Science Laboratories, Kyoto, Japan
** New ** [Slides of Talk]

Further Information

Scott Makeig
Swartz Center for Computational Neuroscience, Institute for Neural Computation, UCSD, USA

Scott's primary research interest is in analysis and modeling of cognitive event-related brain dynamics as captured by high-dimensional EEG, MEG and other brain imaging modalities using Independent Component Analysis, time-frequency and machine learning methods. In particular, he has studied the dynamics of performance and electrophysiology accompanying alertness lapses during sustained monitoring tasks, and has used the results of this research to design real-time alertness monitoring systems, one application in the emerging field of neural human-system interface technology. Currently, he is working to apply Independent Component Analysis to EEG, ERP and fMRI data to open wider windows for noninvasive observation of cognitive brain dynamics.

Scott is Director of the new Swartz Center for Computational Neuroscience of the Institute for Neural Computation, UCSD.

Blind Audio Source Separation based on Independent Component Analysis
Shoji Makino, Hiroshi Sawada, and Shoko Araki

NTT Communication Science Laboratories, Kyoto, Japan
Email: maki@cslab.kecl.ntt.co.jp

This keynote talk describes a state-of-the-art method for the blind source separation (BSS) of convolutive mixtures of audio signals. Independent component analysis (ICA) is used as a major statistical tool for separating the mixtures. We provide examples to show how ICA criteria change as the number of audio sources increases. We then discuss a frequency-domain approach where simple instantaneous ICA is employed in each frequency bin. A directivity pattern analysis of the ICA solutions provides us with a physical interpretation of the ICA-based separation. It tells us the relationship between ICA-based BSS and adaptive beamforming. In order to obtain properly separated signals with the frequency-domain approach, the permutation and scaling ambiguity of the ICA solutions should be aligned appropriately. We describe two complementary methods for aligning the permutations, i.e., collecting separated frequency components originating from the same source.

The first method exploits the signal envelope dependence of the same source across frequencies. The second method relies on the spatial diversity of the sources, and is closely related to source localization techniques.

Finally, we describe methods for sparse source separation, which can be applied even to an underdetermined case.

Last Updated: 21-Sep-2007   Please read our disclaimer