PERLUASAN METODE MFCC 1D KE 2D SEBAGAI ESKTRAKSI CIRI PADA SISTEM IDENTIFIKASI PEMBICARA MENGGUNAKAN HIDDEN MARKOV MODEL (HMM)

Authors

Agus Buono, Departemen Ilmu Komputer, FMIPA, IPB, Kampus IPB Darmaga, Bogor 16680, IndonesiaFollow
Wisnu Jatmiko, Laboratorium Kecerdasan Komputasional, Fakultas Ilmu Komputer, Universitas Indonesia, Depok 16424, Indonesia
Benyamin Kusumoputro, Laboratorium Kecerdasan Komputasional, Fakultas Ilmu Komputer, Universitas Indonesia, Depok 16424, IndonesiaFollow

Abstract

The Extention of MFCC Technique from 1D to 2D as Feature Extractor for Speaker Identification System Using HMM. In this paper, we introduce an extension of Mel-Frequency Cepstrum Coefficients (1D-MFCC) methodology to bispectrum data, referred to as 2D-MFCC, for feature extraction. 2D-MFCC is based on 2D bispectrum data rather than 1D spectrum vector yielded by Fourier transform, so the filter in 1D-MFCC must be extend to 2D filter and using 2D cosine transform to get the mel-cepstrum coefficients from the filtered bispectrum values. Based on 2D-MFCC, we develop a speaker recognition system with Hidden Markov Model (HMM) as classifier. The experimental results show that the recognition rate is around 88%, 92% and 99% for 20, 40 and 60 data training, respectively

References

[1] T.D. Ganchev, Ph.D. Thesis. Wire Communications Laboratory, Department of Computer and Electrical Engineering, University of Patras, Greece, 2005. [2] A. Buono, Sistem Identifikasi Pembicara dengan MFCC sebagai Pengekstraksi Ciri dengan Hidden Markov Model sebagai Classifier, Laporan Teknis Penelitian, Lab. Kecerdasan Komputasional, Fakultas Ilmu Komputer Universitas Indonesia, 2008, tidak dipublikasikan. [3] C.L. Nikeas, A.P. Petropulu, Higher Order Spectra Analysis: A Nonlinear Signal Processing Framework, Prentice-Hall, Inc., New Jersey, 1993, p. 14. [4] M.I. Fanany, B. Kusumoputro, Thesis Magister, Ilmu Komputer, Fasilkom Universitas Indonesia, Depok, 1998. [5] N. Hidayat, B. Kusumoputro, Tesis Magister, Ilmu Komputer, Fasilkom Universitas Indonesia, Depok, 1999. [6] A. Triyanto, B. Kusumoputro, Thesis Magister, Ilmu Komputer, Fasilkom Universitas Indonesia, Depok, 2000. [7] C. Cornaz, U. Hunkeler, An Automatic Speaker Recognition System, Ecole Polytechnique, Federale De Lausanne, http://www.ifp.uiuc.edu/~ minhdo/teaching/speaker_recognition, 2005. [8] L.R. Rabiner, A Tutorial on Hidden Markov Model and Selected Applications in Speech Recognition, Proceeding IEEE 77/2 (1989) 257. [9] M. Nilsson, M. Ejnarsson, Master Thesis, Departement of Telecommunications and Signal Processing, Blekinge Institute of Technology, Ronneby, 2002

Recommended Citation

Buono, Agus; Jatmiko, Wisnu; and Kusumoputro, Benyamin (2009) "PERLUASAN METODE MFCC 1D KE 2D SEBAGAI ESKTRAKSI CIRI PADA SISTEM IDENTIFIKASI PEMBICARA MENGGUNAKAN HIDDEN MARKOV MODEL (HMM)," Makara Journal of Science: Vol. 13: Iss. 1, Article 16.
Available at: https://scholarhub.ui.ac.id/science/vol13/iss1/16