In this book, the research is concerned with the identification of people (mainly speaker verification) based on a connectionist approach. In particular, the book focuses on the improvement of system performance obtained by certain developments of preprocessed speech signal inputs. Various performance measures are used to evaluate the automatic speaker verification (SV) system for different aspects of performance. The book provides an introduction to the field of automatic speaker recognition. The basic structures as well as classification of the speaker recognition systems are described. The task descriptions for SV such as fixed text, text independent and text prompted are described. This book is also concerned with the application of neural network (NN) models to SV. A hybrid neural network is proposed for speaker verification (SV). The basic idea in this system is the usage of vector quantization preprocessing as the feature extractor. The preprocessing stage measures local spectral similarities and uses this information to train the multi layer perceptrons (MLP). The benefit of this SV systems are its speed and simplicity.