Speech activity detection for the automated speaker recognition system of critical use

Journal Title: Журнал інженерних наук - Year 2017, Vol 4, Issue 1

Abstract

In the article, the authors developed a method for detecting speech activity for an automated system for recognizing critical use of speeches with wavelet parameterization of speech signal and classification at intervals of “language”/“pause” using a curvilinear neural network. The method of wavelet-parametrization proposed by the authors allows choosing the optimal parameters of wavelet transformation in accordance with the user-specified error of presentation of speech signal. Also, the method allows estimating the loss of information depending on the selected parameters of continuous wavelet transformation (NPP), which allowed to reduce the number of scalable coefficients of the LVP of the speech signal in order of magnitude with the allowable degree of distortion of the local spectrum of the LVP. An algorithm for detecting speech activity with a curvilinear neural network classifier is also proposed, which shows the high quality of segmentation of speech signals at intervals "language" / "pause" and is resistant to the presence in the speech signal of narrowband noise and technogenic noise due to the inherent properties of the curvilinear neural network.

Authors and Affiliations

M. Bykov, V. Kovtun, O. Maksimov

Keywords

Related Articles

Comprehensive Approach for Identification of Nonlinear Stiffness Characteristics of Bearing Supports for the Oxidizer Turbopump of the Liquid Rocket Engine

This article dials with the refinement of the mathematical and computational models of the oxidizer turbopump rotor considering bearing gaps, axial preloading, compliance of the housing parts and the effect of rotation....

Modern materials for automotive industry

The car industry uses a tremendous number of materials to build cars, including iron, aluminum, steel, glass, rubber, petroleum products, copper, steel and others. These materials have evolved greatly over the decades, b...

Mathematical simulation of fluid flow and analysis of flow pattern in the flow path of low-head Kaplan turbine

The results of numerical investigation of spatial flow of viscous incompressible fluid in flow part of Kaplan turbine PL20 Kremenchug HPP at optimum setting angle of runner blade φb = 15° and at maximum setting angle φb...

Contact stresses on the rake face of cutting tools with PCBN in turning of hardened steel

The paper presents the results of experimental study of determination of the geometric parameters of the contact zone of the chips with the rake face of cutting tools, as well as the shrinkage of chips during the final t...

Numerical Simulation of the Evaporative Air Cooler with a Capillary-Porous Structure

Application of evaporative air cooling in various technologies allows reducing energy costs for improving environmental performance. Considering the promise of using air coolers with a capillary-porous structure, a mathe...

Download PDF file
  • EP ID EP240052
  • DOI -
  • Views 90
  • Downloads 0

How To Cite

M. Bykov, V. Kovtun, O. Maksimov (2017). Speech activity detection for the automated speaker recognition system of critical use. Журнал інженерних наук, 4(1), 14-20. https://europub.co.uk/articles/-A-240052