Speech activity detection for the automated speaker recognition system of critical use | Journal of Engineering Sciences

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

Author(s): Bykov M. M., Kovtun V. V., Maksimov O. O.

Affilation(s): Vinnytsia National Technical University, 95 Khmelnytske Av., 21021, Vinnytsia, Ukraine

*Corresponding Author’s Address: vntu0113055@gmail.com

Issue: Volume 4; Issue 1 (2017)

Dates:
Paper received: April 18, 2017
The final version of the paper received: May 25, 2017
Paper accepted online: May 29, 2017

Citation:
Bykov M. M. Speech activity detection for the automated speaker recognition system of critical use / M. M. Bykov, V. V. Kovtun, O. O. Maksimov // Journal of Engineering Sciences. —  Sumy : Sumy State University, 2017. — Volume 4, Issue 1. — P. H14-H20.

DOI: 10.21272/jes.2017.4(1).h3

Research Area: Computer Engineering

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 speechsignal of narrowband noise and technogenic noise due to the inherent properties of the curvilinear neural network.

Keywords: automated speaker recognition system of critical use, speech activity detection, wavelet transformation, convolution neural network.

Full Text




Scientific journal "The Journal of Engineering Sciences"
ISSN 2312-2498 (Print), ISSN 2414-9381 (Online).

Faculty of Technical Systems and Energy Efficient Technologies
Sumy State University