DETEKSI SUARA UCAPAN SALAM BAHASA ARAB MENGGUNAKAN MEL FREQUENCY CEPSTRAL COEFFICIENT (MFCC) DAN PEMILIHAN FITUR MIN MAX

Heriyanto Heriyanto

Abstract


Abstract
Arabic greeting sounds are used in everyday life for Muslims in Indonesia. Salam recognition is used to check how correct the pronunciation of Arabic greetings is for Indonesians. The first stage was to collect the sample of greeting readings as much as 50 records of male and female records in wav recordings. One person takes the source of greeting reading as a reference for reference. Retrieval of test data as much as 50 samples of test data. The second stage is to perform feature extraction with MFCC from cepstral coefficient and frame results. The third stage is testing by checking the suitability of the greeting reading with the calculation of min max. The result of checking the suitability of reading on the selection of the right features carried out by MFCC has a result of 60.25%. Meanwhile, MFCC with a minimum yield of 71.75.0%. This shows that the use of the min max test can improve accuracy because there are more unique cepstral and max and min coefficients with a significant difference of 11.5%.
Keywords : checking, feature extraction, reference, features, speech
Suara ucapan salam bahasa Arab digunakan dalam kehidupan sehari-hari bagi umat beragama Islam di Indonesia. Pengenal ucapan salam dilakukan untuk mengecek seberapa benar dalam pelafalan ucapan salam berbahasa Arab bagi orang Indonesia. Tahap pertama dilakukan pengambilan sampel bacaan salam sebanyak 50 data rakaman putra dan putri dalam rekaman wav. Pengambilan sumber bacaan salam diambil satu orang sebagai acuan untuk referensi. Pengambilan data uji sebanyak 50 sampel data uji. Tahap kedua adalah melakukan ekstraksi ciri dengan MFCC hasil cepstral coeficient dan frame. Tahap ketiga adalah pengujian dengan pengecekan kesesuaian bacaan salam dengan perhitungan min max. Hasil pengujian pengecekan kesesuaian bacaan terhadap pemilihan fitur yang tepat dilakukan dengan MFCC mempunyai hasil sebesar 60,25%. Sedangkan MFCC dengan min max hasil sebesar 71.75,0%. Hal tersebut menunjukkan bahwa penggunaan pengujian min max dapat meningkatkan akurasi karena terdapat cepstral dan coefficients max dan min lebih unik dengan selisih 11.5% cukup signifikan
Kata Kunci : pengecekan, ekstraksi ciri, referensi, fitur, ucapan


Keywords


pengecekan; ekstraksi ciri; referensi; fitur; ucapan

Full Text:

PDF

References


Abriyono & Harjoko, A. (2012). Pengenalan Ucapan Suku Kata Bahasa Lisan Menggunakan Ciri LPC, MFCC, dan JST. Indonesian Journal of Computing and Cybernetics Systems, 6(2), 23–34.

Aibinu, A. M., Salami, M. J. E., Najeeb, A. R., Azeez, J. F., & Rajin, S. M. A. K. (2011). Evaluating the effect of voice activity detection in isolated Yoruba word recognition system. 2011 4th International Conference on Mechatronics: Integrated Engineering for Industrial and Societal Development, ICOM’11 - Conference Proceedings, May, 17–19. https://doi.org/10.1109/ICOM.2011.5937134

Chamidy, T. (2016). Metode Mel Frequency Cepstral Coeffisients (MFCC) Pada klasifikasi Hidden Markov Model (HMM) Untuk Kata Arabic pada Penutur Indonesia. Matics, 8(1), 36–39.

Chitode, D. J. . (2010). 01.Communication Theory.

Darma Putra, A. R. (2011). Verifikasi Biometrika Suara Menggunakan Metode MFCC dan DTW. LONTAR KOMPUTER Biometrika, Universitas Udayana ISSN:2088-1541, 2(1), 8–21.

Davis, S. B., & Mermelstein, P. (1980). Comparison of Parametric Representations for Monosyllabic Word Recognition in Continuously Spoken Sentences. IEEE Transactions on Acoustics, Speech, and Signal Processing, 28(4), 357–366. https://doi.org/10.1109/TASSP.1980.1163420

Hassan, T., Wassim, A., & Bassem, M. (2007). Analysis and Implementation of an Automated Delimiter of " Quranic " Verses in Audio Files using Speech Recognition Techniques. Robust Speech Recognition and Understanding, June, 352–362. https://doi.org/10.5772/4759

Heriyanto, H.-, Hartati, S., & Putra, A. E. (2018). Evaluation of Suitability of Voice Reading of Al-Qur’an Verses Based on Tajwid Using Mel Frequency Cepstral Coefficients (MFCC) and Normalization of Dominant Weight (NDW). Advances in Image and Video Processing, 6(2). https://doi.org/10.14738/aivp.62.4268

Heriyanto, H. (2019). Deteksi Ucapan Angka Satu Sampai Sepuluh Bahasa Palembang Menggunakan Mfcc Dan Bobot Dominan. Telematika, 16(1), 52. https://doi.org/10.31315/telematika.v16i1.3024

Heriyanto, H., & Simanjuntak, O. S. (2017). Identifikasi Ucapan Warna Menggunakan LPC (Linier Predictive Code ) Dan Kelompok Pemilihan Bobot. Telematika, 14(01), 68–73. https://doi.org/10.31315/telematika.v14i01.1968

Hidayat, S., Hidayat, R., & Adji, T. B. (2015). Sistem Pengenal Tutur Bahasa Indonesia Berbasis Suku Kata Menggunakan MFCC, Wavelet Dan HMM. Conference on Information Technology and Electrical Engineering (CITEE), September, 246–251.

Holmes, J. H. and W. (2003). Speech Synthesis and Recognition, Second Edition. https://doi.org/10.1145/1185448.1185459

Kumar, A. A. (2013). Digital signal processing. In Published by Asoke K. Ghosh, PHI Learning Private Limited, M-97, Connaught Circus, New Delhi-110001 and Printed by Rajkamal Electric Press, Plot No. 2, Phase IV, HSIDC, Kundli-131028, Sonepat, Haryana (Vol. 23, Issue 4). Prentice-Hall of India Pvt.Ltd. https://doi.org/10.1109/TASSP.1975.1162707

Laha, D. (2007). Handbook of Computational Intelligence in Manufacturing and Production Manajemen.

Miftahuddin, Y., & Hakim, M. R. (2017). COEFFICIENT DAN DYNAMIC TIME WARPING UNTUK PENGENALAN NADA PADA ALAT MUSIK BELLYRA. 120–127.

Proakis, J. G., & Manolakis, D. G. (1996). Digital Signal Processing: Principles, algorithms, and applications. In Digital Signal Processing: Principles, algorithms, and applications.

Putra, A. E. (2008). Frekuensi Cuplik pada FFT. Tan Li, Processing, Digital Signal, 1.

Rabiner, L. R., & Schafer, R. W. (2007). Introduction to digital speech processing. In Foundations and Trends in Signal Processing (Vol. 1, Issue 1). https://doi.org/10.1561/2000000001

Smith, S. W. (2000). Digital signal processing. In The Scientist and Engineer’s Guide to Digital Signal Processing (Vol. 17, Issue 2). https://doi.org/10.1109/79.826412

Tokunbo Ogunfunmi, R. T. M. (Sim) narasimha. (2015). Speech and Audio Processing and Recognition (Issue part 1). springer.

Tshilidzi Marwala. (2012). Condition Monitoring Using Computational Intelligence Methods. https://doi.org/10.1007/978-1-4471-2380-4

Vladimir Britanak, Patrick C.Yip, K. R. R. (2007). Discrete Cosine and Sine Transform.

Yanto, H. Y. (2015). Analisa Deteksi Huruf Hijaiyah Melalui Voice Recognition Menggunakan Kombinasi Energy. Telematika, 12(1), 11–22. https://doi.org/10.31315/telematika.v12i1.523

lan Ucapan Suku Kata Bahasa Lisan Menggunakan Ciri LPC, MFCC, dan JST. Indonesian Journal of Computing and Cybernetics Systems, 6(2), hal.23–34.


Refbacks

  • There are currently no refbacks.