The transition to democracy in South Africa has brought with it certain challenges. The main challenge is to get rid of crime and corruption. The paper presents a technique to combat white-collar crime in telephone transactions by identifying and verifying speakers using artificial neural networks (ANNs). Results are presented to show that speaker identification is feasible and this is illustrated with two different types of ANN architectures and with two different types of characteristic features as inputs to ANNs.

Meeting Name

IEEE-INNS-ENNS International Joint Conference on Neural Networks, 2000. IJCNN 2000


Electrical and Computer Engineering

Keywords and Phrases

South Africa; Feature Extraction; Feedforward Neural Nets; Fraud; Linear Predictive Coding; Multilayer Perceptrons; Pattern Matching; Short Distance Telephone Lines; Signal Classification; Speaker Recognition; Telephone Transactions; Text-Dependent Speaker Identification Methods; White-Collar Crime

Document Type

Article - Conference proceedings

Document Version

Final Version

File Type





© 2000 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.

Publication Date

01 Jan 2000