GROUP DELAY BASED MAGNITUDE SQUARE COHERENCE ESTIMATION BY AN ARMA MODEL

In this paper, a new method of estimation of the magnitude square cohe rence function (MSC) by an ARMA model is proposed. The estimation is a chieved by modeling the periodogram estimate of the MSC and the ARMA m odel has been realized by the pole-zero decomposition property of the group delay function (GDF). Its performance has been found to be super ior to that of the periodogram MSC estimate in terms of normalized sum of the sample mean square error (NSSMSE) and maximum sample root mean square error (RMSE). Further, its performance is comparable with thos e of the existing ARMA based estimation methods and requires less comp utations. The proposed ARMA-MSC estimation is simple and does not invo lve any explicit solution of a system of equations.