Identifikasi Pola Suara Pada Bahasa Jawa Meggunakan Mel Frequency Cepstral Coefficients (MFCC)

Istian Kriya Almanfaluti (Institut Sains dan Teknologi Terpadu Surabaya, Surabaya)
Judi Prajetno Sugiono (Institut Sains dan Teknologi Terpadu Surabaya, Surabaya)

JURNAL MEDIA INFORMATIKA BUDIDARMA
Vol 4, No 1 (2020): Januari 2020

Voice Recognition is a process of developing systems used between computer and human. The purpose of this study is to find out the sound pattern of a person based on the spoken Javanese language. This study used the Mel Frequency Cepstral Coefficients (MFCC) method to solve the problem of feature extraction from human voices. Tests were carried out on 4 users consisting of 2 women and 2 men, each saying 1 word "KUTHO", the word pronounced 5 times. The results of the testing are to get a sound pattern from the characteristics of 1 person with another person so that research using the MFCC method can produce different sound patterns