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

Increasing the Speed of Fractal Image Compression Using Two-Dimensional Approximating Transformations

Fractal image compression algorithm is known for allowing very high compression rates (the best examples – up to 1 000 times with acceptable visual quality) for real photos of natural objects, which is not possible for o...

Galerkin–Vlasov Method for Deflection Analysis of Isotropic Sandwich Plates under Uniform Load

In this work, the Galerkin–Vlasov method was used to solve the governing partial differential equation of equilibrium for isotropic sandwich plates with simply supported edges (x = ±a, y = ±b) and under uniform load on t...

Sulfur Utilization in the Systems of Biological Wastwater Denitrification

This paper focuses on the study of the possibility of using mineral carriers from sulfur (bio-sulfur/elementary sulfur) in anaerobic wastewater treatment systems under autotrophic denitrification conditions. The theoreti...

Optimization of controlled damages on the recognition in the master education

Information considered extreme learning algorithm is able to study decision support system as part of the automated control system combined heat and power unit with optimized control tolerances recognition. Within the fr...

Finite Element Analysis of Orthogonal Cutting Forces in Machining AISI 1020 Steel Using a Carbide Tip Tool

Force modeling in metal cutting is important for various purposes, including thermal analysis, tool life estimation, chatter prediction, and tool condition monitoring. Numerous approaches have been proposed to model meta...

Download PDF file
  • EP ID EP240052
  • DOI -
  • Views 99
  • 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