Adaptive Noise Cancellation from Speech Signals using Variablestep Sizealgorithm

Abstract

Noise cancellation from the speech signal is the most importanttask in applications like communications, hearing aids, speech therapy and many others. This allows providing good resolution speech signal to the user. The speech signals are mostlycontaminated due to the several natural as well as manmade noises. As the characteristics of these noises random in its nature filtering techniques with fixed coefficients are not suitable for noise cancellation task. Hence, in this work an adaptive noise canceller algorithmhas driven for enhancement of speech signal applications which has the capability to update its weight coefficients based on the statistical nature of the undesired component in the actual speech signal. In our experiments in order to achieve better convergence rate as well as filtering capability we propose Step Variable Least Mean Square (SVLMS) algorithm instead of constant step parameter. The computational complexity of the speech enhancement process is also a key aspect due to the excessive length of the speech signals in realistic scenario. Hence, to reduce the computational complexity of the proposed mechanism we used Sign Regressor SVLSM (SRSVLMS), which is a hybrid realization of familiar sign regressor algorithm and the proposed SVLMS. Using these two techniques noise cancellation models are developed and tested on real speech signals with unwanted noise contaminations. The experimental outputsconfirm that the SRSVLMS based speech signal enhancement unit performs better than its counterpart with respect to convergence rate, computational complexity and signal to noise ratio increment.