Design of adaptive envelope-constrained filters in the presence of impulsive noise

The problem of designing adaptive filters subject to output envelope constr aints in the presence of impulsive noise at the input channel is investigat ed. Median smoothing is incorporated into the recently developed adaptive e nvelope constrained filtering algorithms with a view to suppressing the eff ect of impulsive noise. It is demonstrated that the proposed adaptive filte ring algorithms can provide notable improvements in the performance. In par ticular, the output envelope constraints of primary interest can be more ea sily satisfied by the filter weight estimate obtained with the median smoot hing than with the average smoothing in impulsive noise situations. Numeric al simulations are included to show the effectiveness of the proposed adapt ive filtering algorithms.