Least mean M-estimate algorithms for robust adaptive filtering inimpulse noise

摘要

This paper proposes two gradient-based adaptive algorithms, callednthe least mean M estimate and the transform domain least mean M-estimaten(TLMM) algorithms, for robust adaptive filtering in impulse noise. Anrobust M-estimator is used as the objective function to suppress thenadverse effects of impulse noise on the filter weights. They have ancomputational complexity of order O(N) and can be viewed, respectively,nas the generalization of the least mean square and the transform-domainnleast mean square algorithms. A robust method fur estimating thenrequired thresholds in the M-estimator is also given. Simulation resultsnshow that the TLMM algorithm, in particular, is more robust andneffective than other commonly used algorithms in suppressing the adverseneffects of the impulses