Pengenalan Jenis Kelamin Manusia Berbasis Suara  Menggunakan MFCC dan GMM

Faisal Dharma Adhinata; Diovianto Putra Rakhmadani; Alon Jala Tirta Segara

doi:10.20895/dinda.v1i1.198

Faisal Dharma Adhinata Institut Teknologi Telkom Purwokerto https://orcid.org/0000-0002-2624-173X
Diovianto Putra Rakhmadani Institut Teknologi Telkom Purwokerto
Alon Jala Tirta Segara Institut Teknologi Telkom Purwokerto

DOI: https://doi.org/10.20895/dinda.v1i1.198

Keywords: voice, gender, machine learning, MFCC, GMM

Abstract

Biometric information that exists in humans is unique from one human to another. One of the biometric data that is easily obtained is the human voice. The human voice is identic data that can differentiate between individuals. When we hear human voices directly, it is easy for our ears to tell the person who is speaking is male or female. But sometimes male voices can resemble girls and vice versa. Therefore, we propose a human voice detection system through Artificial Intelligence (AI) in machine learning. In this study, we used the Mel Frequency Cepstrum Coefficients (MFCC) method to extract human voice features and Gaussian Mixture Models (GMM) for the classification of female or male voice data. The experiment results showed that the system built was able to detect human gender through biometric voice data with an accuracy of 81.18%.