Analisis Speaker Recognition Menggunakan Metode Dynamic Time Warping (DTW) Berbasis Matlab

Abstract

Voice is one of  way to communicate and express yourself. Speaker recognition is a process carried out by a device to recognize the speaker through the voice. This study designed a speaker recognition system that was able to identify speakers based on what was said by using dynamic time warping (DTW) method based in matlab. To design a speaker recognition system begins with the process of reference data and test data. Both processes have the same process, which starts with sound recording, preprocessing, and feature extraction. In this system, the Fast Fourier Transform (FFT) method is used to extract the features. The results of the feature extraction process from the two data will be compared using the DTW method. Calculations using DTW that produce the smallest value will be determined as the output. The test results show that the system can identify the voice with the best level of recognition accuracy of 90%, and the average recognition accuracy of 80%. The results were obtained from 50 tests, carried out by 5 people consisting of 3 men and 2 women, each speaker said a predetermined word

Keywords

Speaker Recognition, Dynamic Time Warping, Fast Fourier Transform.

Full Text:

PDF

References

Atmawati, M.J.T.(2016).Pengenalan suara instrumen musik menggunakan analisis spektrum, Universitas Sanata Dharma. Yogyakarta.

Brigham, E. O. (1988).The Fast Fourier Transform And Its Applications. Prentice Hall Inc. United States of America.

Dinata, C., Puspitaningrum, D. (2017).Implementasi Teknik Dynamic Time Warping (DTW) Pada Aplikasi Speech To Text.Program Studi Teknik Infomatika Universitas Bengkulu. Bengkulu.

Gunawan, D., Juwono, F.H,. (2012).Pengolahan Sinyal Digital Dengan Pemrograman Matlab. Graha ilmu, Yogyakarta.

Handoko, D.T.(2018).Aplikasi Keamanan PC dengan Voice Recognition Menggunakan Metode MFCC dan Dynamic Time Warping (DTW).Universitas Nusantara PGRI Kediri. Kediri.

Hapsari, J.P.(2011).Aplikasi Pengenalan Suara Dalam Pengaksesan Sistem Informasi Akademik. UniversitasDiponegoro. Semarang.

Kurniawan, I. (2009). Pengolahan Sinyal, Politeknik Jambi. Jambi.

Kurniawan. (2016). Identifikasi Speech Recognition Manusia dengan Menggunakan Average Energy dan Silent Ratio Sebagai Feature Extraction Suara pada Komputer, Universitas Jambi, Jambi.

Mathworks. (2019).Dynamic Time Warping (DTW). Online.

https://www.mathworks.com/help/signal/ref/dtw.html?s_tid=srchtitle, diakses pada tanggal 15 Mei 2019

Mathworks.(2019).Hamming Window. Online.

https://www.mathworks.com/help/signal/ref/hamming.html?searchHighlight=Hamming&s_tid=doc_srchtitle, diakses pada tanggal 15 Mei 2019

Mulyani, R.(2017).Pemetaan Dan Analisis Tipe Suara Manusia Menggunakan Fast Fourier Transform (FFT) Studi Kasus Ukm Psm Unila, Fakultas Matematika Dan Ilmu Pengetahuan Alam Universitas Lampung, Bandar Lampung.

Munir, R.(2004).Pengolahan Citra Digital Dengan Pendekatan Algoritmik. Penerbit Informatika, Bandung.

Nurlaily. (2009).Pencocokan Pola Suara Dengan Algoritma FFT Dan DC.Fakultas Matematika Dan Ilmu Pengetahuan Alam Universitas Sumatera Utara, Medan.

Permana, I.S., Nurhasanah, Y.I., Zulkarnain, A.(2018).Implementasi Metode MFFC Dan DTW Untuk Pengenalan Jenis Suara Pria Dan Wanita.Teknik Informatika Institut Teknologi Nasional Bandung. Bandung

Rianto, J.(2011).Perangkat Pengenalan Suara (Voice Recognition) Untuk Absensi Karyawan Dengan Menggunakan Metode Dynamic Time Warping (DTW). Universitas Komputer Indonesia, Bandung.

Santoso, T.B., Octavianto, H., Huda, M.(2010).Praktikum pengolahan sinyal digital. Institut Teknologi Sepuluh November, Surabaya.

Setyawan, Y.R.(2014).Pengenalan Ucapan Angka Secara Real Time Menggunakan Ekstraksi Ciri FFT dan Fungsi Similaritas Kosinus.Universitas Sanata Dharma, Yogyakarta.

Sibarani, R.A.L. (2018). Identifikasi Sinyal Suara Menggunakan Metode Fast Fourier Transfoem (FFT) Berbasis Matlab. Universitas Sumatera Utara, Medan.

Sukono, A.(2015).Algoritma Dynamic Programming dalam Pengenalan Suara, Program Studi Teknik InformatikaSekolah Teknik Elektro dan Informatika Institut Teknologi Bandung, Bandung.

Triansyah, E., Indrawaty, Y.(2017).Implementasi Metode Pattern Recognition Untuk Pengenalan Ucapan Huruf Hijaiyya., Institut Teknologi Nasional, Malang.

http://dx.doi.org/10.28989/avitec.v1i1.492

Article Metrics

Abstract view: 923 times
Download     : 1431   times

This work is licensed under a Creative Commons Attribution 4.0 International License.

Refbacks

• There are currently no refbacks.