Automatic Speaker Verification using Artificial Neural Networks

This book is presenting a fresh look into the field of automatic speaker verification technique via artificial neural networks. It is intended as a text for postgraduate students in applied physics, electrical and electronics engineering. It can exclusively serve as a reference for the scientists who are working in the area of automatic speaker verification/identification techniques. Traditional password or token based authentication schemes are insecure and are being replaced by biometric authentication mechanisms. Voiceprints were one of the first biometrics to be widely used. And artificial neural network is one of the most efficient, speedy and reliable tool by which an automatic speaker verification (ASV) system can be developed. The primary aim of this book is to describe an ASV system using artificial neural network which can be used in security purpose, criminal identification, etc. The primary intends are to increase the speed of the system maintaining optimum accuracy and improve its noise performance.