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.
G. K. Venayagamoorthy and N. Sundepersadh, "Comparison of Text-Dependent Speaker Identification Methods for Short Distance Telephone Lines using Artificial Neural Networks," Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks, 2000. IJCNN 2000, Institute of Electrical and Electronics Engineers (IEEE), Jan 2000.
The definitive version is available at https://doi.org/10.1109/IJCNN.2000.861466
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
Article - Conference proceedings
© 2000 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.