Robust modeling of acoustic paths using a sparse adaptive algorithm

Abstract Acoustic impulse response functions are generally sparse in nature and traditionally these are modeled by adaptive finite impulse response (FIR) filters trained using a least mean square (LMS) algorithm. The conventional LMS algorithm is not effective in modeling sparse systems and sparse LMS algorithms have been recently developed to improve the modeling in such scenarios. However, the traditional sparse LMS algorithms are not robust to disturbances at the error sensor and may diverge in some scenarios. With an objective to overcome this limitation of conventional sparse adaptive algorithm, this paper presents a robust sparse adaptive algorithm. The new algorithm has been shown to effectively model sparse systems in a robust manner. In addition, the algorithm has been successfully applied in modeling the acoustic feedback path in a behind the ear digital hearing aid.

[1]  Johan Hellgren,et al.  Analysis of feedback cancellation in hearing aids with Filtered-x LMS and the direct method of closed loop identification , 2002, IEEE Trans. Speech Audio Process..

[2]  Alberto González,et al.  A biased multichannel adaptive algorithm for room equalization , 2012, 2012 Proceedings of the 20th European Signal Processing Conference (EUSIPCO).

[3]  Rodrigo C. de Lamare,et al.  Sparsity-aware pseudo affine projection algorithm for active noise control , 2014, Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014 Asia-Pacific.

[4]  Alfred O. Hero,et al.  Sparse LMS for system identification , 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

[5]  Ali H. Sayed,et al.  Sparse Distributed Learning Based on Diffusion Adaptation , 2012, IEEE Transactions on Signal Processing.

[6]  Zhaoyang Zhang,et al.  Diffusion Sparse Least-Mean Squares Over Networks , 2012, IEEE Transactions on Signal Processing.

[7]  Luis Weruaga,et al.  Exact NLMS Algorithm with ${\ell _p}$-Norm Constraint , 2015, IEEE Signal Processing Letters.

[8]  Vahid Tarokh,et al.  Adaptive algorithms for sparse system identification , 2011, Signal Process..

[9]  Bernard Widrow,et al.  Adaptive Signal Processing , 1985 .

[10]  Mrityunjoy Chakraborty,et al.  A zero attracting proportionate normalized least mean square algorithm , 2012, Proceedings of The 2012 Asia Pacific Signal and Information Processing Association Annual Summit and Conference.

[11]  Guillermo Sapiro,et al.  Robust anisotropic diffusion , 1998, IEEE Trans. Image Process..

[12]  Ganapati Panda,et al.  A robust filtered-s LMS algorithm for nonlinear active noise control , 2012 .

[13]  Rodrigo C. de Lamare,et al.  Sparsity-Aware Filtered-X Affine Projection Algorithms for Active Noise Control , 2014, ArXiv.

[14]  Fumiyuki Adachi,et al.  Sparse least mean fourth algorithm for adaptive channel estimation in low signal‐to‐noise ratio region , 2014, Int. J. Commun. Syst..

[15]  Sergios Theodoridis,et al.  Online Sparse System Identification and Signal Reconstruction Using Projections Onto Weighted $\ell_{1}$ Balls , 2010, IEEE Transactions on Signal Processing.

[16]  Milos Doroslovacki,et al.  Improving convergence of the PNLMS algorithm for sparse impulse response identification , 2005, IEEE Signal Processing Letters.