Sparse Multichannel Source Localization and Separation
2008 (English)In: / [ed] The Institute of Mathematics and its Applications, Cirencester: The Institute of Mathematics and its Applications , 2008, 90-93 p.Conference paper (Refereed)
The DUET and DESPRIT blind source separation algorithms attempt to recover J sources from I mixtures of these sources, in the interesting case where J > I, with minimal information about the mixing environment of underling sources statistics. We present a semi-blind generalization of the DUET-DESCRIPT approach which allows arbitary placement of the sensors and demixes the sources given the room impulse response. We learn a sparse representation of the mixtures on an over-complete spatial signatures dictionary. We localize and separate the constituent sources via binary masking of a power weighted histogram in location space or in attenuation-delay space. We demonstrate the robustness of this technique using synthetic room experiments.
Place, publisher, year, edition, pages
Cirencester: The Institute of Mathematics and its Applications , 2008. 90-93 p.
Sparse Signal Processing; Blind Source Separation; Time-Frequency Analysis
Research subject Applied and Computational Mathematics
IdentifiersURN: urn:nbn:se:kth:diva-175440OAI: oai:DiVA.org:kth-175440DiVA: diva2:860976
8th International Conference on Mathematics in Signal Processing
QC 201512162015-10-142015-10-142015-12-16Bibliographically approved