Fast spatio-temporal decorrelation using FIR filter network with decoupled adaptive step sizes

Abstract Blind separation of convolutive mixtures has many applications in the areas of acoustics, communications, biomedical signal processing. Spatio-temporal decorrelation is a useful preprocessing technique that can reduce the blind separation problem into a simpler orthogonal matrix estimation problem. However, it is computationally expensive for its large unknown parameter set. Realtime spatio-temporal decorrelation method remains an open issue for years. In this paper, we focus on accelerating the adaptation process in the FIR filter based decorrelation method. Firstly, the update equation is decoupled into spatial decorrelation and temporal decorrelation. Then, their respective convergence conditions are systematically analyzed using eigenvalue decomposing method. Based on it, a fast algorithm for FIR filter network with spatio-temporal decoupled adaptive step-sizes is proposed. Comprehensive simulations are performed on both synthetic data and real world captured sEMG data. We have compared the proposed algorithm with the fixed step size method, IIR filter with natural gradient, and the annealed step size method. The factors including number of iteration, number of channel, computational time, selection of filter order and window size are elaborately compared and discussed. The results verified the reliable performance of our method on accelerating the adaptation process for spatio-temporal decorrelation simultaneously compared to classical methods.

[1]  Manfredo Atzori,et al.  Electromyography data for non-invasive naturally-controlled robotic hand prostheses , 2014, Scientific Data.

[2]  Allan Kardec Barros,et al.  independent , 2006, Gumbo Ya Ya.

[3]  Andrzej Cichocki,et al.  Robust neural networks with on-line learning for blind identification and blind separation of sources , 1996 .

[4]  Aapo Hyvärinen,et al.  A Fast Fixed-Point Algorithm for Independent Component Analysis , 1997, Neural Computation.

[5]  Jean-Christophe Pesquet,et al.  Convolutive Blind Signal Separation Based on Asymmetrical Contrast Functions , 2007, IEEE Transactions on Signal Processing.

[6]  Scott C. Douglas,et al.  An Adaptive Constraint Method for Paraunitary Filter Banks with Applications to Spatiotemporal Subspace Tracking , 2007, EURASIP J. Adv. Signal Process..

[7]  Andrzej Cichocki,et al.  Neural networks for blind decorrelation of signals , 1997, IEEE Trans. Signal Process..

[8]  Andrea Cavallaro,et al.  Pseudo-Determined Blind Source Separation for Ad-hoc Microphone Networks , 2018, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[9]  Jie Zhu,et al.  Anti-Hebbian learning in topologically constrained linear networks: a tutorial , 1993, IEEE Trans. Neural Networks.

[10]  Shun-ichi Amari,et al.  Natural Gradient Works Efficiently in Learning , 1998, Neural Computation.

[11]  Hiroshi Sawada,et al.  Spatio–Temporal FastICA Algorithms for the Blind Separation of Convolutive Mixtures , 2007, IEEE Transactions on Audio, Speech, and Language Processing.

[12]  Philippe Loubaton,et al.  Adaptive subspace algorithm for blind separation of independent sources in convolutive mixture , 2000, IEEE Trans. Signal Process..

[13]  Philippe Loubaton,et al.  Blind identification of MIMO-FIR systems: A generalized linear prediction approach , 1999, Signal Process..

[14]  Jun Peng,et al.  Using Joint Generalized Eigenvectors of a Set of Covariance Matrix Pencils for Deflationary Blind Source Extraction , 2018, IEEE Transactions on Signal Processing.

[15]  Seungjin Choi,et al.  Natural Gradient Learning for Spatio-Temporal Decorrelation: Recurrent Network , 2000 .

[16]  Dario Farina,et al.  Decoding the neural drive to muscles from the surface electromyogram , 2010, Clinical Neurophysiology.