zbMATH — the first resource for mathematics

The LOST algorithm: Finding lines and separating speech mixtures. (English) Zbl 1153.94301
Summary: Robust clustering of data into linear subspaces is a frequently encountered problem. Here, we treat clustering of one-dimensional subspaces that cross the origin. This problem arises in blind source separation, where the subspaces correspond directly to columns of a mixing matrix. We propose the LOST algorithm, which identifies such subspaces using a procedure similar in spirit to EM. This line finding procedure combined with a transformation into a sparse domain and an \(L_{1}\)-norm minimisation constitutes a blind source separation algorithm for the separation of instantaneous mixtures with an arbitrary number of mixtures and sources. We perform an extensive investigation on the general separation performance of the LOST algorithm using randomly generated mixtures, and empirically estimate the performance of the algorithm in the presence of noise. Furthermore, we implement a simple scheme whereby the number of sources present in the mixtures can be detected automatically.
94-04 Software, source code, etc. for problems pertaining to information and communication theory
94A13 Detection theory in information and communication theory
68T10 Pattern recognition, speech recognition
BSS Eval; Soft-LOST
Full Text: DOI
[1] doi:10.1016/0165-1684(94)90029-9 · Zbl 0791.62004 · doi:10.1016/0165-1684(94)90029-9
[2] doi:10.1162/089976601300014385 · Zbl 0985.94004 · doi:10.1162/089976601300014385
[3] doi:10.1162/neco.1995.7.6.1129 · Zbl 05479838 · doi:10.1162/neco.1995.7.6.1129
[4] doi:10.1109/78.554307 · doi:10.1109/78.554307
[5] doi:10.1162/neco.1997.9.7.1483 · doi:10.1162/neco.1997.9.7.1483
[7] doi:10.1016/j.neucom.2003.09.008 · Zbl 02060571 · doi:10.1016/j.neucom.2003.09.008
[9] doi:10.1109/TSP.2006.881199 · Zbl 1375.94040 · doi:10.1109/TSP.2006.881199
[12] doi:10.1155/2007/24717 · Zbl 1168.94449 · doi:10.1155/2007/24717
[13] doi:10.1016/S0165-1684(01)00120-7 · Zbl 0985.94006 · doi:10.1016/S0165-1684(01)00120-7
[14] doi:10.1002/ima.20035 · doi:10.1002/ima.20035
[15] doi:10.1137/S1064827596304010 · Zbl 0919.94002 · doi:10.1137/S1064827596304010
[17] doi:10.1109/LSP.2005.843759 · doi:10.1109/LSP.2005.843759
[18] doi:10.1109/TSP.2004.828896 · Zbl 1369.94383 · doi:10.1109/TSP.2004.828896
[19] doi:10.1155/2007/86484 · Zbl 1168.94427 · doi:10.1155/2007/86484
[20] doi:10.1016/j.sigpro.2007.02.003 · Zbl 1186.94042 · doi:10.1016/j.sigpro.2007.02.003
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.