Adaptive Filters
Subband Adaptive Filtering: Theory and Implementation
Subband Adaptive Filtering: Theory and Implementation
A variable step-size matrix normalized subband adaptive filter
IEEE Transactions on Audio, Speech, and Language Processing
A PNLMS algorithm with individual activation factors
IEEE Transactions on Signal Processing
Inherent Decorrelating and Least Perturbation Properties of the Normalized Subband Adaptive Filter
IEEE Transactions on Signal Processing
A New Robust Variable Step-Size NLMS Algorithm
IEEE Transactions on Signal Processing
Proportionate Affine Projection Sign Algorithms for Network Echo Cancellation
IEEE Transactions on Audio, Speech, and Language Processing
Hi-index | 0.08 |
Sign algorithms (SAs) have attracted much attention because of their robustness against impulsive interference. To reduce the computational cost of SAs, a sign subband adaptive filter (SSAF) has recently been proposed. However, the SSAF converges slowly and the convergence rate of the SSAF does not increase with the number of subbands. In this paper, two variants of the SSAF, called the affine projection SSAF (AP-SSAF) and the proportionate SSAF (P-SSAF), are proposed to solve this problem. The AP-SSAF updates the tap-weight vector based on several previous input vectors, which can not only maintain robustness against impulsive interference, but also increase the convergence rate for both white and colored input signals; the P-SSAF incorporates a gain distribution matrix into the SSAF to proportionately adapt the tap-weight vector of the adaptive filter, which can both maintain robustness against impulsive interference and increase the convergence rate of the SSAF for sparse system identification. Simulation results are presented to demonstrate the improved performance of the AP-SSAF and the P-SSAF.