Abstract
Speaker recognition consists of three phases: pre-processing, feature extraction and classification. During the first phase, the computer records the voice pattern of the speaker and analyse it. By the end of the second phase, the main features of the voice pattern are extracted. In the third phase, many classification techniques are exist such as artificial neural network (ANN), hidden Markov model (HMM) and vector quantization (VQ). Classifiers based on ANN are used in both text dependent and text independent speaker identification and speaker verification systems. Furthermore, it is extremely efficient at learning complex mappings between input and outputs. Unfortunately, ANN technique is complex and time consuming. In this paper, we use two different feature extraction techniques. These techniques are MFCC and PNCC. In addition, we use principle component analysis (PCA) as a feature reduction technique to enhance the classifier performance and speed. We apply ANN for both techniques with different training algorithms. The best results are achieved using PNCC as a feature extraction, the ANN as a classifier with sequential weight/bias training algorithm. Our proposed technique decreases the number of neurons that lead to have best performance and processing time.