ResearchBib Share Your Research, Maximize Your Social Impacts
Sign for Notice Everyday Sign up >> Login

AUTOMATIC INITIAL SEGMENTATION OF SPEECH SIGNAL BASED ON SYMMETRIC MATRIX OF DISTANCES

Journal: INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY (Vol.15, No. 4)

Publication Date:

Authors : ; ; ; ; ;

Page : 4782-4791

Keywords : Speech signal; Initial segmentation; Symmetric matrix of distances; Pseudo inverse matrix; Moore-Penrose algorithm; Singular decomposition; Euclidean; Chebyshev and cosine metrics; Measure of similarity.;

Source : Downloadexternal Find it from : Google Scholarexternal

Abstract

The most common issue of a speech signals analisys and artificial intelligence systems development is determining of temporal and frequency charactristics. That’s because any undetermined signal is defined as a nonlinear object. But it is always possible to select time interval from the signals with a given discretization period. Such an interval is called quasistationary interval. The quasistationary interval in combination with the speech signal quality characteristics can be used to build a parametric model of the speech signal. As a result, such a model will be very helpful for solving different issues of artificial intelligence development processes. In this paper the method of an initial segmentation of the speech signal via quasistationary intervals by threshold deviation of algebraic specifications of elementary areas is presented. The latter method of automatic initial segmentation is based on pseudorotation of symmetric matrix of distances and evaluation criteria. The problem and process of selection the quasistationary intervals are described in the section 1.

Last modified: 2014-08-07 02:47:52