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: [email protected]
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.
