A Simplified RLS Algorithm and Its Application in Acoustic Echo Cancellation

In some adaptive filtering applications, the recursive least-squares (RLS) algorithm may be too computationally and memory intensive to implement. In this paper, a new RLS algorithm based on set membership with partial-update is presented. The new algorithm allows the reduction of the frequency of updates of the filter coefficients, where the filter coefficients are updated such that the output estimation error is upper bounded by a pre-determined threshold. Moreover, in this algorithm, the combination of the partial-update with set-membership focuses on updating a selected subset of the filter coefficients per iteration because the computational complexity is proportional to the number of filter coefficients. The resulting algorithm capitalizes not only from the sparse updating related to the set-membership framework but also from the partial update of the coefficients, reducing the average computational complexity. Simulation experiments in a typical echo cancellation environment confirm the effectiveness of the proposed algorithm.