‘Shadow BSS’ for Blind Source Separation in Rapidly Time-Varying Acoustic Scenes

Wehr S, Lombard A, Buchner H, Kellermann W (2007)


Publication Language: English

Publication Type: Conference contribution

Publication year: 2007

Publisher: Springer-Verlag

City/Town: Berlin, Heidelberg

Pages Range: 560-568

Event location: London GB

ISBN: 978-3-540-74494-8

DOI: 10.1007/978-3-540-74494-8_70

Abstract

This paper addresses the tracking capability of blind source separation algorithms for rapidly time-varying sensor or source positions. Based on a known algorithm for blind source separation, which also allows for simultaneous localization of multiple active sources in reverberant environments, the source separation performance will be investigated for abrupt microphone array rotations representing the worst case. After illustrating the deficiencies in source-tracking with the given efficient implementation of the BSS algorithm, a method to ensure robust source separation even with abrupt microphone array rotations is proposed. Experimental results illustrate the efficiency of the proposed concept.©2007 Springer

Authors with CRIS profile

How to cite

APA:

Wehr, S., Lombard, A., Buchner, H., & Kellermann, W. (2007). ‘Shadow BSS’ for Blind Source Separation in Rapidly Time-Varying Acoustic Scenes. In Mike E. Davis, Christopher J. James, Samer A. Abdallah (Eds.), Proceedings of the 7th International Conference on Independent Component Analysis and Signal Separation (pp. 560-568). London, GB: Berlin, Heidelberg: Springer-Verlag.

MLA:

Wehr, Stefan, et al. "‘Shadow BSS’ for Blind Source Separation in Rapidly Time-Varying Acoustic Scenes." Proceedings of the 7th International Conference on Independent Component Analysis and Signal Separation, London Ed. Mike E. Davis, Christopher J. James, Samer A. Abdallah, Berlin, Heidelberg: Springer-Verlag, 2007. 560-568.

BibTeX: Download