Analisis Fungsi Wavelet Daubechies untuk Sinyal Suara dengan Panjang Segmen Berbeda

  • Habib Ratu Perwira Negara
  • Syahroni Hidayat
  • Danang Tejo Kumoro
Keywords: wavelet, wavelet Daubechies N order (dbN), cross-correlation


Wavelets Daubechies have been widely applied to signal processing, such as automatic speech recognition system. Wavelet Daubechies, which is one of the wavelet families distinguished by its order, defined as N. The magnitude of the order N value has an influence on the wavelet decomposition where with the greater N value there is an increase in the smoothness of multiresolution analysis results. However, not all order Daubechies wavelet can give the same good recognition results so that its application still such as trial and error. Therefore, it is necessary to determine the order of the Daubechies wavelet base function on the Indonesian voice signal through its similarity level. The method can be used to determine the similarity level between speech signal and wavelet Daubechies function N order by calculating its crosscorrelation coefficient. The result shows that there is inconcistency of the best wavelet daubechies basis function for Indonesian vowels a,i,u,e,è,o, and ò. Which db45 and db44 are the best wavelet Daubechies basis function on 2048 and 1024 segmentation length respectively.


[1] C. R. Rashmi, “Review of Algorithms and Applications in Speech Recognition System,” Int. J. Comput. Sci. Inf. Technol., vol. 5, no. 4, pp. 5258–5262, 2014.
[2] M. A. Anusuya and S. K. Katti, “Front end analysis of speech recognition: a review,” Int. J. Speech Technol., vol. 14, no. 2, pp. 99–145, Jan. 2011.
[3] S. Hidayat, R. Hidayat, and T. B. Adji, “SPEECH RECOGNITION OF KV-PATTERNED INDONESIAN SYLLABLE USING MFCC, WAVELET AND HMM,” J. Ilm. Kursor, vol. 8, no. 2, pp. 67–78, 2015.
[4] R. Hidayat, Priyatmadi, and W. Ikawijaya, “Wavelet based feature extraction for the vowel sound,” in 2015 International Conference on Information Technology Systems and Innovation, ICITSI 2015 - Proceedings, 2015, pp. 1–4.
[5] O. Farooq and S. Datta, “Phoneme recognition using wavelet based features,” in Information Sciences, 2003, vol. 150, no. 1–2, pp. 5–15.
[6] J. Rafiee, M. A. Rafiee, N. Prause, and M. P. Schoen, “Wavelet basis functions in biomedical signal processing,” Expert Syst. Appl., vol. 38, no. 5, pp. 6190–6201, 2011.
[7] J. Rafiee, P. W. Tse, A. Harifi, and M. H. Sadeghi, “A novel technique for selecting mother wavelet function using an intelligent fault diagnosis system,” Expert Syst. Appl., vol. 36, no. 3, pp. 4862–4875, 2009.
[8] J. Rafiee and P. W. Tse, “Use of autocorrelation of wavelet coefficients for fault diagnosis,” Mech. Syst. Signal Process., vol. 23, pp. 1554–1572, 2009.
[9] International Phonetic Association, “IPA Learning Tool.” [Online]. Available: http://www.internationalphoneticalp [Accessed: 01-Jan- 2015].
[10] S. Hidayat, U. Hasanah, and A. A. Rizal, “Algoritma Penghapus Derau / Silence Dan Penentuan Endpoint Dengan Nilai Ambang Terbobot Untuk Sinyal Suara,” in Seminar Nasional APTIKOM (SEMNASTIKOM), 2016, no. October 2016, pp. 320–323.
[11] S. Poornima, “Basic Characteristics of Speech Signal Analysis,” Int. J. Innov. Res. Dev., vol. 5, no. 4, pp. 1–5, 2016.
[12] X. Huang, A. Acero, and H.-W. Hon, Spoken Language Processing: A Guide to Theory, Algorithm and System Development. Prentice Hall, 2001.
[13] V. K. Ingle and J. G. Proakis, Digital Signal Processing using MATLAB, 3rd ed. USA: CENGAGE Learning, 2012.
[14] N. Ahuja, S. Lertrattanapanich, and N. K. Bose, “Properties determining choice of mother wavelet,” in IEE Proc.-Vis. Image Signal Process., 2005, vol. 152, no. 5.
[15] PYWAVELET, “WAVELET BROWSER.” [Online]. Available: /db3/. [Accessed: 21-May-2015].