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 analysis of the mechanical system "fixture - workpiece"

Present work is devoted to locating and clamping of prismatic parts in fixtures during the machining on drilling-milling-boring machines. The special feature of locating schemes of parts of the present type is that one o...

Polymeric compositional materials based on polycarbonate for units of devices for transform solar into thermal energy

Modern development of the industry is complicated without introduction of energy-saving technologies based on renewable natural energy sources. Solar and wind power plants, heat generators, solar collectors are wide spre...

Influence of quenching temperature from the intercritical interval on the character of X70 steel strain hardening

The article presents the analysis of the diagrams of X70 steel tension, previously normalized and quenched in water from intercritical А1-А3 interval, there were calculated the degree of hardening, evenly elongation and...

Overview of Control Techniques for Multicellular Converter

The structure multicellular converters, which appeared at the beginning of the 1990s, makes it possible to share the constraints in tension and it also improves the harmonic contents of the wave forms. To benefit as well...

Application of Rough TOPSIS Technique for the Analysis of Engineering System Failure Causes

The prioritization of the causes of engineering system failure posed to be a challenge. Therefore, there is a need to develop a tool that will be used to identify critical problems of an engineering system to facilitate...

Download PDF file
  • EP ID EP240052
  • DOI -
  • Views 75
  • 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