Speaker Recognition Using Mel Frequency Cepstral Coefficient and Self-Organising Fuzzy Logic

Speaker recognition is a biometric technique based on the voice characteristics. Mel Frequency Cepstral Coefficients (MFCC) is one of the methods that used for extracting the features on speaker recognition system, where this method turn the voice into features characteristics that imitating the characteristics of human hearing. Self-Organising Fuzzy Logic (SOF) is a development of the fuzzy logic method. This paper discusses the combination of MFCC and the offline stage of SOF for increasing the accuracy of the system. 10 peoples are pronouncing the same keyword for text-dependent system, 300 voice data from 10 peoples consisting of 30 data for each people was used. After the data has been extracted at MFCC and normalized, the data was multiplied by the SOF covariance matrix for each class, and to obtain the final result K-Nearest Neighbour (KNN) was chosen. The accuracy performance of the system achieved 97,15. © 2021 Elsevier B.V., All rights reserved.