Convex Combination of Overlap-Save Frequency-Domain Adaptive Filters

TL;DR

This paper introduces a convex combination of frequency-domain adaptive filters that reduces computational complexity and improves system identification accuracy across various signal types.

Contribution

It proposes a novel COSFDAF algorithm combining FDAFs with convex optimization, including a formula for updating the mixing parameter and theoretical complexity analysis.

Findings

Better steady-state error performance

Reduced computational complexity

Improved identification of unknown coefficients

Abstract

In order to decrease the steady-state error and reduce the computational complexity and increase the ability to identify a large unknown system, a convex combination of overlap-save frequency-domain adaptive filters (COSFDAF) algorithm is proposed. From the articles available, most papers discuss convex combinations of adaptive-filter algorithms focusing on the time domain. Those algorithms show better performances in convergence speed and steady-state error. The major defect of those algorithms, however, is the computational complexity. To deal with this problem and motivated by frequency-domain adaptive filters (FDAF) and convex optimization, this paper gives an adaptive filter algorithm, that consists of combining the two FDAFs using the convex combination principles and derives a formula to update the mixing parameter. The computational complexity of the COSFDAF is analyzed theoretically. The simulation results show that no matter what kinds of signal to be processed, whether correlated (i.e. colored noise) or uncorrelated (i.e. white noise), the proposed algorithm has better performance in identify the unknown coefficients when compared to a single overlap-save FDAF or the convex combination of two time-domain adaptive filters.