Performance analysis of New Time Varying LMS (NTVLMS) adaptive filtering algorithm in noise cancellation system for speech enhancement

摘要

This paper compares the performance analysis of our proposed New Time Varying LMS (NTVLMS) algorithm with other well-known adaptive algorithms such as LMS, NLMS, RVSSLMS and TVLMS algorithm. These algorithms have been tested for their adaptive noise cancellation capabilities in the context of Speech signals corrupted by four variants of noise signals viz White Gaussian noise, Conference noise, Engine noise and Traffic noise. Performance of these algorithms is analyzed based on output SNR. The computer simulation results show that the performance of proposed algorithm is better compared to other algorithms in White Gaussian noise Environment. For the other three noise environments, NLMS algorithm performs well.