A Recursive Least M-Estimate Adaptive Algorithm With Low Complexity for Active Control of Impulsive Noises

Adaptive active control is a crucial technology to attenuate impulsive noises. But how to design an appropriate adaptive filter to attain a flexible compromise between noise reduction and computational complexity is a challenging problem. This paper proposes a robust adaptive filtering algorithm to deal with this issue. The coefficient vector of the adaptive filter is decomposed into two sets of short sub-filters through the Kronecker product, which reduces the size of matrices and vectors in the active noise control algorithm. A robust estimator, which is insensitive to impulsive noises, is used to define a group of cost function under the recursive least-squares criterion, based on which we derive the adaptive control algorithm that is composed of two groups of alternately updating equations. The effectiveness of the proposed approach is verified by numerical simulations.