Speaker identification and verification over short distance telephone l

SPEAKER IDENTIFICATION AND VERIFICATION OVER SHORT distance TELEPHONE LINES USING ARTIFICIAL NEURALNETWORKSGanesh K Venayagamoorthy, N arnd Sunderpersadh, and Theophilus N Andrewgkumarieee.org sunderntelkom.co.za theowpo.mlsultan.ac.zaelectronic Engineering Department,M L Sultan Technikon,P O stroke 1334, Durban, sulphur Africa.ABSTRACTCrime and corruption baffle become uncontrolled todayin our society and countless coin is lost each classdue to exsanguinous collar criminal offense, fraud, and embezzlement.This paper presents a technique of an ongoing workto combat washrag-collar crime in foretelltransactions by identifying and verifying speakersusing Artificial unquiet Networks (ANNs). Resultsare presented to show the potential of this technique.1. INTRODUCTIONSeveral countries today are face rampant crime andcorruption. Countless money is lost each year due towhite collar crime, fraud, and embezzlement. In todays thickening economic times, businesses and individualsare both falling victims to these devastating crimes.Employees embezzle monetary resource or steal goods from theiremployers, then disappear or hide croup legal issues.Individuals can easily become helpless victims ofidentity theft, cable schemes and other scams that robthem of their moneyWhite collar crime occurs in the gray area where thecriminal law ends and gracious law begins. Victims ofwhite collar crimes are faced with navigating a dauntinglegal inner ear in order to effect some sort of resolution orrecovery. Law enforcement is often too focused oncombating street crime or does not have the expertiseto investigate and prosecute forward-looking fallaciousacts. Even if criminal prosecution is pursued, a criminal opinion does not mean that the victims of fraud areable to recover their losses. They have to rely on thcriminal courts awarding restitution later the convictionand by then the perpetrator has disposed of or hidde almost of the assets available for recovery. From t he civillaw perspective, resolution and recovery can safe be adifficult as pursuing criminal prosecution. Perpetratorsof white collar crime are often difficult to locate andserved with civil process. Once the perpetrators havebeen located and served, proof must be provided thatthe fraudulent act occurred and recovery/damages areneeded. This usually takes a lengthened legal fight, whichoften can cost the victim more money than t... ...phone speech, IEEE call for Processing Letters, vol. 2 no. 3 jar against 1995, pp.46 - 48.2 J.M.Naik, L.P.Netsch, G.R.Doddington, Speakerverification over long distance phone lines,Proceedings of IEEE International Conference onAcoustics, Speech, and Signal Processing (ICASSP),23-26 may 1989, pp. 524 - 527.3 A.L.Mcilraith, H.C.Card, Birdsong RecognitionUsing Backpropagation and Multivariate Statistics,Proceedings of IEEE Trans on Signal Processing, vol.45, no. 11, November 1997.4 G.K.Venayagamoorthy, V.Moonasar,K.Sandrasegaran, Voice Recognition Us ing NeuralNetworks, Proceedings of IEEE South AfricanSymposium on Communications and Signal Processing(COMSIG 98), 7-8 September 1998, pp. 29 - 32.5 V.Moonasar, G.K.Venayagamoorthy, Speakeridentification using a combination of differentparameters as feature inputs to an artificial neuralnetwork classifier, accepted for publication in theProceedings of IEEE Africon 99 conference, CapeTown, 29 September 2 October 99.6 H.Demuth, M.Beale, MATLAB Neural NetworkToolbox Users Guide, The Maths Works Inc., 1996.7 T.Kohonen, Self-organizing and bear on memorySpring Verlag, Berlin, third edition, 1989.