Communications on Applied Electronics |
Foundation of Computer Science (FCS), NY, USA |
Volume 6 - Number 9 |
Year of Publication: 2017 |
Authors: Rathnakara.S, V. Udayashankara |
10.5120/cae2017652557 |
Rathnakara.S, V. Udayashankara . Enhancement of Speech Signal using Improved NLMS Algorithm. Communications on Applied Electronics. 6, 9 ( Apr 2017), 34-37. DOI=10.5120/cae2017652557
In this paper a modified robust variable step size algorithm is proposed and the performance of the proposed algorithm is compared with original robust variable step size (RVSS) algorithm. This leads to another derivative of Normalized Least mean square algorithm (NLMS). The performance of the proposed algorithm is measured with additive stationary and nonstationary Gaussian noise with original speech taken by standard IEEE sentence (SP23) of NOIZEUS data base. The output of proposed and RVSS algorithm are measured with excess mean square error (EMSE) in both stationary and non stationary environment. The results can be appreciated that the proposed algorithm gives improved result over RVSS algorithm and also the speed of convergence is maintained same as other NLMS algorithms