Speech Signal Autoregression Modeling Based on the Discrete Fourier Transform and Scale-Invariant Measure of Information Discrimination

In this paper, we consider the problem of autoregressive modeling of a speech signal according to the data of its discrete Fourier transform on intervals of one speech frame (several milliseconds). Based on the information-theoretic approach, a novel method, in which two computational procedures, namely, iterative optimization of autoregressive parameters and their automatic amplitude scaling are separated from each other was developed. A full-scale experiment was set up and carried out. The main advantage of the new method in comparison with its known analogs is shown to be the extremely high rate of convergence of iterations to the optimal solution.