Speaker identification and verification over short distance telephone l

SPEAKER designation AND VERIFICATION OVER SHORTDISTANCE TELEPHONE LINES USING imitation 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 Box 1334, Durban, South Africa.ABSTRACT umbrage and corruption hit become rampant todayin our fraternity and countless coin is lost each yeardue to ashen turn back crime, blind, and embezzlement.This paper presents a technique of an ongoing workto battle white-collar crime in telephonetransactions by identifying and verificatory speakers development Artificial Neural Networks (ANNs). Resultsare presented to show the potential of this technique.1. entranceSeveral countries today are facing rampant crime andcorruption. incalculable money is lost each year due towhite collar crime, fraud, and embezzlement. In todayscomplex economic times, businesses and individualsare some(prenominal) fall ing victims to these devastating crimes.Employees embezzle funds or steal goods from theiremployers, hence disappear or hide behind legal issues.Individuals smoke comfortably become helpless victims ofidentity theft, stock schemes and other scams that robthem of their moneyWhite collar crime occurs in the gray area where the twist fairness ends and civil law begins. Victims ofwhite collar crimes are face with navigating a dauntinglegal maze in order to depression some sort of resolution orrecovery. Law enforcement is often besides focused oncombating street crime or does not have the expertiseto investigate and prosecute sophisticated fraudulentacts. Even if wicked prosecution is pursued, a criminalconviction does not mean that the victims of fraud areable to recover their losses. They have to rely on thcriminal courts awarding restitution after the convictionand by then the perpetrator has disposed of or hiddemost of the assets available for recovery. From the civillaw per spective, resolution and recovery can just be a problematical as pursuing criminal prosecution. Perpetratorsof white collar crime are often difficult to locate andserved with civil process. Once the perpetrators havebeen fixed and served, proof must be provided thatthe fraudulent act occurred and recovery/ restitution areneeded. This usually takes a lengthy legal fight, whichoften can cost the victim more money than t... ...phone speech, IEEESignal touch on Letters, vol. 2 no. 3 March 1995, pp.46 - 48.2 J.M.Naik, L.P.Netsch, G.R.Doddington, Speaker bank check over long distance telephone lines,Proceedings of IEEE International group discussion onAcoustics, Speech, and Signal Processing (ICASSP),23-26 May 1989, pp. 524 - 527.3 A.L.Mcilraith, H.C.Card, Birdsong citation utilise 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 Using NeuralNet works, Proceedings of IEEE South AfricanSymposium on communication theory 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, drapeTown, 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 associate memorySpring Verlag, Berlin, tertiary edition, 1989.