DETEKSI UCAPAN ANGKA SATU SAMPAI SEPULUH BAHASA PALEMBANG MENGGUNAKAN MFCC DAN BOBOT DOMINAN

Heriyanto Heriyanto

Abstract


Abstract Detecting speech with regional language, one of which is Palembang language, has uniqueness and distinctiveness in accent. Differences in dialects to check how precise and influential the accuracy of using MFCC and dominant weights. This study consists of three stages. The first stage, feature extraction of numerical numbers from one to ten using Mel Frequency Cepstral Coefficient (MFCC). The second stage is the selection of features that will be used as feature tables using the proposed model Normalized Dominant Weight (NBD) with threshold similarity, range, filtering, normalization of weights and dominant weights. The third stage is testing by checking by finding similarities in range, filtering, sequential multiplication and calculation of Suitability of Uniformity Patterns (CTF). The test results of checking MFCC and feature selection with normalization of dominant weights were 70% while without feature selection only 42%. Keywords : extraction, weighting, dominant, normalization, range Abstrak Deteksi ucapan dengan berbahasa daerah salah satunya bahasa Palembang mempunyai keunikan dan kekhasan dalam logat berbahasa. Perbedaan logat bahasa untuk mengecekan seberapa tepat dan berpengaruh terhadap akurasi menggunakan MFCC dan Bobot dominan. Penelitian ini terdiri atas tiga tahap. Tahap pertama, ekstraksi ciri angka bahasa angka satu sampai sepuluh menggunakan Mel Frequency Cepstral Coefficient (MFCC). Tahap kedua adalah pemilihan fitur yang akan dijadikan tabel fitur menggunakan model yang diusulkan Normalisasi Bobot Dominan (NBD) dengan kesamaan threshold, jangkauan, filtering, normalisasi bobot dan bobot dominan. Tahap ketiga adalah pengujian dengan pengecekan dengan cara mencari kesamaan jangkauan, filtering, perkalian sekuensial dan perhitungan Kesesuaian Keseragaman Pola (KKP). Hasil pengujian pengecekan terhadap MFCC dan pemilihan fitur dengan normalisasi bobot dominan sebesar 70% sedangkan tanpa pemilihan fitur hanya sebesar 42%. Kata kunci : ekstraksi, bobot, dominan, normalisasi, jangkauan

Keywords


ekstraksi, bobot, dominan, normalisasi, jangkauan.

Full Text:

PDF

References


DAFTAR PUSTAKA

Abriyono dan Harjoko, A., 2012. Pengenalan Ucapan Suku Kata Bahasa Lisan Menggunakan

Ciri LPC, MFCC, dan JST. Indonesian Journal of Computing and Cybernetics Systems,

(2), hal.23–34.

Aibinu, A.M., Salami, M.J.E., Najeeb, A.R., Azeez, J.F. dan Rajin, S.M.A.K., 2011a. 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), hal.17–19.

Chamidy, T., 2016. Metode Mel Frequency Cepstral Coeffisients (MFCC) Pada klasifikasi

Hidden Markov Model (HMM) Untuk Kata Arabic pada Penutur Indonesia. Matics, 8(1),

hal.36–39. Available at: http://ejournal.uinmalang.ac.id/index.php/saintek/article/view/3482.

Davis, S.B. dan 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), hal.357–366.

Heriyanto, 2015. Analisa Deteksi Huruf Hijaiyah Melalui Voice Recognition Menggunakan

Kombinasi Energy. Telematika, 12(1), hal.11–22.

Heriyanto, dkk 2018, Advanced Image Video Processing-Volume 6 No 2 Apr 2018-

AIVP-DOI-DOI: http://dx.doi.org/10.14738/aivp.62.4268

Suyanto, S. dan Putra, A.E., 2014b. Automatic Segmentation of Indonesian Speech into

Syllables using Fuzzy Smoothed Energy Contour with Local Normalization, Splitting, and

Assimilation. Journal of ICT Research and Applications, 8(2), hal.97–112. Available at:

http://journal.itb.ac.id/index.php?li=article_detail&id=1804.

Suyanto dan Hartati, S., 2013. Design of Indonesian LVCSR using Combined Phoneme The

Approaches of LVCSR. Icts, hal.191–196.




DOI: https://doi.org/10.31315/telematika.v16i1.3024

DOI (PDF): https://doi.org/10.31315/telematika.v16i1.3024.g2444

Refbacks

  • There are currently no refbacks.




Copyright of :
TELEMATIKA: Jurnal Informatika dan Teknologi Informasi
ISSN 1829-667X (print); ISSN 2460-9021 (online)


Dipublikasi oleh
Jurusan Teknik Informatika, UPN Veteran Yogyakarta
Jl. Babarsari 2 Yogyakarta 55281 (Kampus Unit II)
Telp: +62 274 485786
email: jurnaltelematika@upnyk.ac.id

 

Jurnal Telematika sudah diindeks oleh beberapa lembaga berikut:
 

 

 

 

 

Status Kunjungan Jurnal Telematika