Simple algorithms for decorrelation-based blind source separation
Tóm tắt
We present simple adaptive algorithms that perform blind source separation for spatially-independent and temporally-correlated source signals. The proposed algorithms are modified versions of a well-known natural gradient prewhitening scheme, and the simplest version has almost the same complexity as this prewhitening method. We provide a stationary point analysis of our schemes, proving that the only locally-stable stationary point results in separated sources with unit variances and a guaranteed output ordering. We also show how to modify the approaches so that joint subspace analysis and decorrelation-based source separation are performed. Simulations verify the separation capabilities of the schemes.
Từ khóa
#Decorrelation #Blind source separation #Source separation #Statistics #Iterative algorithms #Adaptive algorithm #Analysis of variance #Performance analysis #Gradient methods #Algorithm design and analysisTài liệu tham khảo
choi, 2000, Blind separation of nonstationary and temporally correlated sources from noisy mixtures, Proc IEEE Workshop Neural Networks Signal Processing, 405
10.1109/IJCNN.2001.938855
10.1109/78.650109
douglas, 2000, N umerically-robust O(N2) RLS algorithms using least-squares prewhitening, Proc IEEE Int Conf Acoust Speech Signal Processing, i, 412
douglas, 2000, Combined subspace tracking, prewhitening, and contrast optimization for noisy blind signal separation, Proc 2nd Int Workshop Indep Compon Anal Source Separation, 579
10.1162/neco.1997.9.7.1483
10.1109/78.553476
10.1103/PhysRevLett.72.3634
10.1109/31.76486
thawonmas, 1999, Blind signal extraction of arbitrarily distributed by temporally correlated signals-A neural networks approach, IEICE Trans Fund Electron Commun Comp Sci, e82 a, 1834
10.1109/78.554307
amari, 1996, A new learning algorithm for blind signal separation, Adv Neural Inform Proc Sys 8, 757
10.1016/0165-1684(94)90029-9
10.1162/089976600300015079