An algorithm for blind source separation based on several time-delayed second-order correlation matrices is proposed. The technique to construct the unmixing matrix employs first a whitening step and then an approximate simultaneous diagonalisation of several time-delayed second-order correlation matrices. Its efficiency and stability are demonstrated for linear artificial mixtures with 17 sources. 1 Introduction Blind source separation is an increasingly popular data analysis technique. It has been applied successfully to the so called cocktail party problem (e.g. [9, 3, 2, 5, 7, 12, 1]) and to various problems in biomedical data processing (e.g. [10, 13, 14]). Usually it is assumed that the observed signals x are constituted of linearly mixed sources s, which are unknown, but mutually statistically independent. x i (t) = n X j=1 a ij s j (t) 1 i; j n i:e: x = As: (1) Since neither s nor the mixing process A are known and we have to estimate the inverse C of the mixing matrix b...
CITATION STYLE
Ziehe, A., & Müller, K.-R. (1998). TDSEP — an efficient algorithm for blind separation using time structure (pp. 675–680). https://doi.org/10.1007/978-1-4471-1599-1_103
Mendeley helps you to discover research relevant for your work.