Affiliations: [a]
Department of Electronics and Telecommunication Engineering, JSPM’s Rajarshi Shahu College of Engineering, Tathawade, Pune, India
| [b]
G.H. Raisoni Institute of Engineering Technology, Pune, India
Correspondence:
[*]
Corresponding author. Mugdha Dewasthale, Department of Electronics and Telecommunication Engg. JSPM’s Rajarshi Shahu College of Engineering, Tathawade, Pune-411033, India. Tel.: +91 9850971458; E-mail: mugdhamd@yahoo.com.
Abstract: Least Mean Square (LMS) and Normalized-Least Mean Square (NLMS) algorithms are very popular and frequently used algorithms for noise cancellation in speech. But selecting the step size for updating the weight of adaptive filter is the big issue in LMS and NLMS algorithms. So as to meet disagreeing requirements of quick convergence and less MSE, step size needs to be correctly controlled. Along with step size, length of adaptive filter also plays major role in the effective noise cancellation. These two factors greatly affect the performance of the ANC. To get the best possible solution, a variety of trials of filter length and step size are required. The main motivation behind the development of proposed High Performance Self Tuning (HPST) adaptive filter algorithm is to adaptively determine the step size. The selection of length of adaptive filter is based on the distance between two microphones in the ANC system. The proposed algorithm works very well, as shown in the experiments which are carried out on NOIZEUS speech corpus as well as actually recorded noisy speech signals. Results indicate that proposed algorithm is superior to referred algorithms in terms of Mean- Square- Error (MSE), Peak- Signal to Noise ratio (PSNR), convergence time and complexity.
