Automatic Speaker Recognition System Using Fuzzy C-Means Artificial Neural Networks

• Main Authors: M. Z., Ibrahim, Marzuki, Khalid, Rubiyah, Yusof
• 格式: Article
• 語言: English; English
• 出版: Universiti Malaysia Pahang 2008
• 主題: TK Electrical engineering. Electronics Nuclear engineering
• 在線閱讀: http://umpir.ump.edu.my/id/eprint/8755/1/fkee-2008-zamri-%20Automatic%20Speaker%20Recognition%20System.pdf; http://umpir.ump.edu.my/id/eprint/8755/7/fkee-2008-zamri-%20Automatic%20Speaker%20Recognition%20System1.pdf; http://umpir.ump.edu.my/id/eprint/8755/; http://www.ump.edu.my/

Speaker recognition is a process of recognizing someone by their voice. The goal of speaker recognition is to extract, characterize and recognize the information about speaker identity. In this paper, we discussed both Fuzzy C-Means (FCM) and Artificial Neural Network (ANN) approach to speaker recognition system. The proposed system comprises of three main modules, a feature extraction module to extract necessary features from speech waves, speaker modeling module to generate the speaker model and FCM and ANN module to classify the speakers whether to accept or reject. The proposed intelligent learning system has been applied to a case study of text-dependent speaker recognition system and the performance is evaluated by applying two types of feature extraction techniques: Mel Frequency Cepstral Coefficients (MFCC) and Linear Predictive Ceps~ral Coefficients (LPCC). Experiment showed that the new proposed systems provide significantly higher performance compare to conventional method.