Efficiency of the Multidimensional Schur-Type Estimation Algorithms for Higher-Order Stochastic Processes

Non-Gaussian signals (e.g. speech signal, electrocar-diograms) are commonly faced with in real-life. However, most of the signals estimation methods developed so far are based on the linear approach, which is appropriate for Gaussian signals which are not optimal, or adequate, for real-life non-Gaussian signals. Such signals should be approached with nonlinear estimation methods which can significantly improve estimation results. As the nonlinear processing of non-Gaussian signals is a key to enhance the existing as well as to introduce new technologies, in this paper we focus on verifying directions in which increasing number of the linear and nonlinear Schur coefficients results with better estimation results.