IMPROVEMENT OF PERFORMANCE OF MEN AND WOMEN'S VOICE DIFFERENCES BASED ON FREQUENCY USING FUZZY LOGIC METHOD
Along with the development of technology, the technique of identification of human voices based on sex is very necessary for some parties, especially in the field of education. The main parameter in distinguishing male and female voices is the frequency of the same one-word pronunciation sample with the same duration and pressure. To facilitate this, a matlab-based male and female voice differentiator application was designed and the results will be improved by the fuzzy logic method. Based on the application testing, of the 20 human voice samples tested, there was 1 sound sample that was difficult to identify, so the accuracy level was only 95%. However, by using the fuzzy logic method, 1 sound sample can be classified in the form of female voices, so the performance of male and female voice differentiator applications increases to 100%. The final results of this study obtained a range of male voice signal frequencies 81.93 Hz to 233.3 Hz while the frequency range of female voice signals 316.9 Hz to 575.5 Hz.
A. S. Irtawaty, "Implementasi Metode Fast Fourier Transform (FFT) Dalam Mengklasifikasikan Suara Pria dan Wanita di Laboratorium Jurusan," Jurnal Terpadu Teknologi, vol. 7, no. 2, Oktober 2019.
B. Susanto, "Identifikasi Suara Pria dan Wanita berdasarkan Frekuensi Suara," Universitas Kristen Duta Wacana, 2011.
A. Ahmadiyah, "Sistem Rekomendasi Lagu Berdasarkan Jenis Suara Penyanyi Pada Aplikasi Karaoke.," Jurnal Ilmiah Teknologi Informasi, vol. 15, no. 2, pp. 248-255, 2017.
W. Rahim, "Analisis Spektrum Suara Manusia Berdasarkan Jenis Kelamin (Gender) Dan Kelompok Umur Menggunakan Komputer.," Jurnal IOM FMIPA, vol. 2, no. 1, 2015.
T. Sejati, "Klasifikasi Suara Burung Lovebird Dengan Algoritma Fuzzy Logic. e-Proceeding of Engineering," e-Proceeding of Engineering, vol. 2, no. 2, p. 3171, 2015.
Copyright (c) 2020 Jurnal Ecotipe (Electronic, Control, Telecommunication, Information, and Power Engineering)
This work is licensed under a Creative Commons Attribution 4.0 International License.
Submission of a manuscript implies that the submitted work has not been published before (except as part of a thesis or report, or abstract); that it is not under consideration for publication elsewhere; that its publication has been approved by all co-authors. If and when the manuscript is accepted for publication, the author(s) still hold the copyright and retain publishing rights without restrictions. Authors or others are allowed to multiply article as long as not for commercial purposes. For the new invention, authors are suggested to manage its patent before published. The license type is CC-BY 4.0
Jurnal Ecotipe is licensed under a Creative Commons Attribution 4.0 International License.