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

Solving the Nonstationary Problem of the Disperse Phase Concentration during the Pneumoclassification Process of Mechanical Mixtures

The article dials with studying of the gas-dispersed systems classification process in gravitation pneumoclassifiers of prismatic shape. The aim of the research is to determine operating parameters of the investigated pr...

Research of Non-metallic Inclusions Removal in Teeming Ladles of Various Design

It was studied in the article the possibility of intensification of removal of non-metallic inclusions in a teeming ladle during holding without any additional external influences on the metal (argon blowing or electroma...

Adjusting the size of the rope thread in the machining of dimensional tool

The article considers the possibility of adjustment the geometrical deviations profile rope thread with a large pitch, which appear as a consequence of wear of the cutting tool during machining. Due to the fact that the...

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...

Investigation of influence of drying agent movement on the drying process effectiveness in the gravitational shelf dryer

The article stands for a research of the drying process efficiency of various approaches of reciprocal movement organization of drying agent and disperse material. It focuses on the results of shelf dryer investigation....

Download PDF file
  • EP ID EP240052
  • DOI -
  • Views 102
  • 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