A novel noise cancellation method for speech enhancement using variable step-size adaptive algorithm

Abstract

This paper presents a general variable step-size (VSS) adaptive filter. The variable step-size normalized least mean square (VSSNLMS) and VSS affine projection algorithms (VSSAPA) are particular examples of adaptive algorithms covered by this generic adaptive filter. Then, a new VSS partial rank (VSSPR) adaptive filter algorithm based on the generic VSS adaptive filter is introduced for noise cancellation in speech enhancement. The proposed algorithm has faster convergence rate and lower steady state mean square error compare with ordinary PRA. The good performance of the new algorithm is demonstrated via simulation results in attenuating the noise.