Multidimensional localization of multiple sound sources using averaged directivity patterns of blind source separation systems

Lombard A, Rosenkranz T, Buchner H, Kellermann W (2009)


Publication Language: English

Publication Status: Published

Publication Type: Conference contribution, Conference Contribution

Publication year: 2009

Pages Range: 233-236

Article Number: 4959563

Event location: Taipei TW

ISBN: 978-1-4244-2353-8

DOI: 10.1109/ICASSP.2009.4959563

Abstract

In this paper, we propose a versatile acoustic source localization framework exploiting the self-steering capability of Blind Source Separation (BSS) algorithms. We provide a way to produce an acoustical map of the scene by computing the averaged directivity pattern of BSS demixing systems. Since BSS explicitly accounts for multiple sources in its signal propagation model, several simultaneously active sound sources can be located using this method. Moreover, the framework is suitable to any microphone array geometry, which allows application for multiple dimensions, in the near field as well as in the far field. Experiments demonstrate the efficiency of the proposed scheme in a reverberant environment for the localization of speech sources. ©2009 IEEE.

Authors with CRIS profile

Involved external institutions

How to cite

APA:

Lombard, A., Rosenkranz, T., Buchner, H., & Kellermann, W. (2009). Multidimensional localization of multiple sound sources using averaged directivity patterns of blind source separation systems. In Proceedings of the 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009 (pp. 233-236). Taipei, TW.

MLA:

Lombard, Anthony, et al. "Multidimensional localization of multiple sound sources using averaged directivity patterns of blind source separation systems." Proceedings of the 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009, Taipei 2009. 233-236.

BibTeX: Download