METHODS FOR QUALITY ENHANCEMENT OF USER VOICE SIGNAL IN VOICE AUTHENTICATION SYSTEMS

O. N. Faizulaieva, I. S. Nevlyudov


Read the full article 

Abstract

The reasonability for the usage of computer systems user voice in the authentication process is proved. The scientific task for improving the signal/noise ratio of the user voice signal in the authentication system is considered. The object of study is the process of input and output of the voice signal of authentication system user in computer systems and networks. Methods and means for input and extraction of voice signal against external interference signals are researched. Methods for quality enhancement of user voice signal in voice authentication systems are suggested. As modern computer facilities, including mobile ones, have two-channel audio card, the usage of two microphones is proposed in the voice signal input system of authentication system. Meanwhile, the task of forming a lobe of microphone array in a desired area of voice signal registration (100 Hz to 8 kHz) is solved. The usage of directional properties of the proposed microphone array gives the possibility to have the influence of external interference signals two or three times less in the frequency range from 4 to 8 kHz. The possibilities for implementation of space-time processing of the recorded signals using constant and adaptive weighting factors are investigated. The simulation results of the proposed system for input and extraction of signals during digital processing of narrowband signals are presented. The proposed solutions make it possible to improve the value of the signal/noise ratio of the useful signals recorded up to 10, ..., 20 dB under the influence of external interference signals in the frequency range from 4 to 8 kHz. The results may be useful to specialists working in the field of voice recognition and speaker’s discrimination.


Keywords: authentication, array, biometrics, direction pattern, voice signal, quadrature processing, microphone

References
1.          Gmurman V.E. Teoriya veroyatnostei i matematicheskaya statistika [Probability theory and mathematical statistics]. Moscow, Vysshaya Shkola Publ., 1999, 479 p.
2.          Teoreticheskie osnovy radiolokatsii[Theoretical foundations of radiolocation]. Ed. Ya.D. Shirman. Moscow, Sov. radio Publ.,1970, 560 p.
3.          Pastushenko O.N., Nevlyudov I.Sh. Analiz kachestvennykh pokazatelei biometricheskikh system autentifikatsii pol’zovatelei [Qualitative analysis of biometric systems for users authentication]. Problemy telekommunikatsii, 2012, no. 4 (9), pp. 96-103.
4.          Murthy H.A., Beaufays F., Heck K.P., Weintraub M. Robust text-independent speaker identification over telephone channels. IEEE Transactions on Speech and Audio Processing, 1999, vol. 7, no. 5, pp. 554-568. doi: 10.1109/89.784108
5.          Wang L., Kitaoka N., Nakagawa S. Robust distant speaker recognition based on position-dependent CMN by combining speaker-specific GMM with speaker-adapted HMM. Speech Communication, 2007, vol. 49, no. 6, pp. 501-513. doi: 10.1016/j.specom.2007.04.004
6.          Mokretsov A.V. Algoritm i ustroistvo s adaptivnym upravleniem kharakteristikoi napravlennosti na osnove prostranstvenno vremennoi obrabotki signalov. Avtoref. diss. kand. tekhn. nauk [Algorithm and device with adaptive control of directivity pattern based on the space-time signal processing. PhD eng. sci. diss. abstract].  Taganrog, 2012, 16 p.
7.          Sorokin V.N., V’yugin V.V., Tananykin A.A. Raspoznavanie lichnosti po golosu: analiticheskii obzor [Individual voice recognition: an analytical review]. Informatsionnye protsessy,2012, vol.12, no. 1,pp. 1-30.
8.          Monzingo R.A., Miller T.W. Introduction to adaptive arrays. SciTech Publishing, Inc.,2003,544 p.
9.          Losev Yu.I. Berdnikov A.G., Goikhman E.Sh., Sizov B.D. Adaptivnaya kompensatsiya pomekh v kanalakh svyazi [Adaptive interference compensation in the communication channels]. Moscow, Radio i svyaz' Publ., 1988, 208 p.
10.       Besacier L., Bonastre J.-F. Subband architecture for automatic speaker  recognition. Signal Processing, 2000, vol. 80, no. 7, pp. 1245-1259. doi: 10.1016/S0165-1684(00)00033-5
11.       Lu X., Dang J. An investigation of dependencies between frequency components and speaker characteristics for text-independent speaker identification. Speech Communication, 2007, vol. 50, no. 4, pp. 312-322. doi: 10.1016/j.specom.2007.10.005
12.       Belousova E.E., Pastushenko N.S., Pastushenko O.N. Analiz vliyaniya chastoty diskretizatsii na kachestvo formirovaniya kvadraturnoi sostavlyayushchei analiticheskogo signala [Analysis of the sampling rate influence on quality of quadrature component forming of the analytical signal]. Vostochno-Evropeiskii zhurnal peredovykh tekhnologii, 2013, vol. 1, no. 9 (61), pp. 8-13.
13.        Widrow B. Adaptive noise cancelling: principles and applications. Proceedings of the IEEE, 1975, vol. 63, no. 12, pp. 1692-1716. doi: 10.1109/PROC.1975.10036
14.       Belousova E.E., Pastushenko O.N. Analiz vliyaniya chastoty diskretizatsii na kachestvo formirovaniya kvadraturnoi sostavlyayushchei dlya nekotorykh signalov [Analysis of the sampling rate influence on quality of quadrature component forming of the some signals]. Radiotekhnika, 2013, no. 172, pp. 141-146
Copyright 2001-2017 ©
Scientific and Technical Journal
of Information Technologies, Mechanics and Optics.
All rights reserved.

Яндекс.Метрика