The Principle of the Information-Divergence Minimum in the Problem of Spectral Analysis of the Random Time Series Under the Condition of Small Observation Samples
- 30 Downloads
We consider the issue of small observation samples in the problem of spectral analysis of the random time series. It is proposed to solve the considered problem using the information-theoretic approach and a new algorithm based on the principle of minimum divergence of the cognominal spectral estimates yielded by the results of several independent observations in the Kullback–Leibler information metric. An example of a practical realization of the algorithm is considered and its asymptotic properties are studied.
KeywordsPower Spectral Density Speech Signal Information Divergence Speech Database Accuracy Index
Unable to display preview. Download preview PDF.
- 2.V. A. Kovrigin and B. I. Shakhtarin, Methods of Spectral Estimation of Random Processes [in Russian], Goryachaya Liniya–Telekom, Moscow (2011).Google Scholar
- 5.D.Yu. Akat’ev and V.V. Savchenko, Avtometriya, No. 2, 68 (2005).Google Scholar
- 6.V.V. Savchenko and D.A.Ponomarev, Avtometriya, No. 1, 56 (2009).Google Scholar
- 8.B.M. Vovshin, V.V. Lavrukevich, and A.V. Semenyaka, in: Proc. 8th Int. Sci. Pract. Conf. “Modern Information and Electronic Technologies,” Odessa, 2012, p. 157.Google Scholar
- 9.P. H. M´’uller, P. Neumann, and R. Storm, Tafeln der Mathematischen Statistik, VEB Fachbuchverlag, Leipzig (1973).Google Scholar
- 11.V.V. Savchenko, D.Yu.Akat’ev, I.V.Gubochkin, et al., “Information system of phonetic analysis of continuous speech: Computer program,” Patent No. 2008615442 RF [in Russian], Application No. 2008614233 of September 15, 2008.Google Scholar