Model Pengenalan Suara Teks Bebas Menggunakan Algoritma Support Vector Machine

 Muhammad Bobbi Kurniawan Nasution (Universitas Al Washliyah Labuhanbatu, Rantauprapat, Indonesia)
 Kusmanto Kusmanto (Universitas Al Washliyah Labuhanbatu, Rantauprapat, Indonesia)
 Sudi Suryadi (Universitas Al Washliyah Labuhanbatu, Rantauprapat, Indonesia)
 (*)Ronal Watrianthos Mail (Universitas Al Washliyah Labuhanbatu, Rantauprapat, Indonesia)

(*) Corresponding Author

Submitted: August 31, 2020; Published: October 21, 2020

DOI: http://dx.doi.org/10.30865/mib.v4i4.2436

Abstract

Voice authentication can be done because there are physical differences in the voice production organs of each person. The user's spoken sound pattern can be used as a voice command as desired. Some features such as accents, intonation, and the way pronunciation produce different patterns. For identification verification, voice data is divided into two groups: voice with defined text and voice with free text. Sounds resulting from the pronunciation of a particular word can be changed from analog to digital form. This change process will result in representation in vector form. One technique in voice recognition classification is the Support Vector Machine (SVM). The study aims to develop SVM algorithms to create free text-based speech patterns, recognition models. The sound pattern classification process uses three kernels for the data set so that the comparison results will be more accurate. The highest accuracy in the linear kernel is found in the 4th loop in the third fold with an accuracy rate of 94.40%. While in the polynomial kernel the highest accuracy at the 6th iteration of the second fold with an accuracy of 96.80%. The highest accuracy rate is found in the RBF kernel on the 8th loop of the third fold with 98.20% accuracy. These test results prove the RBF kernel has the best level of accuracy in free text-based speech recognition.

Keywords


Voice, Autentication, RBF, Support Vector Machine, SVM

Full Text:

PDF


Article Metrics

Abstract View: 69 times | PDF View: 17 times

References

I. Agustina, Fauziyah, and A. Gunaryati, “Biometrik Pola Suara Dengan Jaringan Saraf Tiruan,” J. Tek. Inform., vol. 9, no. 2, pp. 140–147, 2016.

R. Umar, I. Riadi, and A. Hanif, “Analisis Bentuk Pola Suara Menggunakan Ekstraksi Ciri Mel-Frequencey Cepstral Coefficients (MFCC),” CogITo Smart J., vol. 4, no. 2, p. 294, 2019, doi: 10.31154/cogito.v4i2.130.294-304.

T. Kinnunen and H. Li, “An Overview of Text-Independent Speaker Recognition : from Features to Supervectors,” Speech Commun., vol. 52, no. 1, 2009.

M. Hebert, “Text-dependent speaker recognition,” in In Springer handbook ofspeech processing, 2009, pp. 743–762.

A. Azene, “Text-independent speaker identification for the amharic language,” 2015.

S. Gustina, A. Fadlil, and R. Umar, “Sistem Identifikasi Jamur Menggunakan Metode Ekstraksi Ciri Statistik Orde 1 dan Klasifikasi Jarak,” Techno.COM, vol. 16, no. 378–386, 2017.

M. Nasution, D. Irmayani, R. Watrianthos, S. Suryadi, and I. R. Munthe, “Comparative Analysis Of Data Mining Using The Rought Set Method With K-Means Method,” Int. J. Sci. Technol. Res., vol. 8, no. 05, pp. 38–40, 2019, [Online]. Available: http://www.ijstr.org/final-print/may2019/Comparative-Analysis-Of-Data-Mining-Using-The-Rought-Set-Method-With-K-means-Method.pdf.

E. Riyanto and Sutejo, “Perbandingan Metode Ekstraksi Ciri Suara MFCC, ZCPA, dan LPC, HIMSYATECH,” J. Teknol. Inf., vol. 10, no. 1, 2014.

Muhammad Habib ur Rehman, C. S. Liew, A. Abbas, P. P. Jayaraman, T. Y. Wah, and S. U. Khan, “Big Data Reduction Methods: A Survey,” Data Sci. Eng., vol. 1, no. 4, pp. 265–284, 2016, doi: 10.1007/s41019-016-0022-0.

K. HB and S. TK, “Speech Data Compression Using Vector uantization,” WASET Int. J. Comput. Inf. Sci. Eng., vol. 2, no. 4, pp. 251–254, 2008.

Nijhawan G and P. P, “Isolated Speech Recognition using MFCC and DTW,” Int. J. Adv. Res. Electr. Electron. Instrum. Eng., vol. 2, no. 8, pp. 4085–4092, 2013.

N. Smith and M. Gales, “Speech Recognition using SVMs,” in Advances in Neural Information Processing Systems 14, 2001.

M. DBA, B. SZ, and E. N, “Evaluation of SVM Kernels and Conventional Machine Learning Algorithms for Speaker Identification,” Int. J. Hybrid Inf. Technol., vol. 3, no. 3, pp. 23–34, 2010.

R. B. Handoko and S. Suyanto, “Klasifikasi Gender Berdasarkan Suara Menggunakan Support Vector Machine,” Indones. J. Comput., vol. 4, no. 1, p. 9, Mar. 2019, doi: 10.21108/INDOJC.2019.4.1.244.

T. Chamidy, “Metode Mel Frequency Cepstral Coeffisients (MFCC) Pada klasifikasi Hidden Markov Model (HMM) Untuk Kata Arabic pada Penutur Indonesia,” MATICS, vol. 8, no. 1, pp. 36–39, 2016.

D. Astuti, “Aplikasi Identifikasi Suara Hewan Menggunakan Metode Mel-Frequency Cepstral Coefficients (MFCC),” J. Informatics, Inf. Syst. Softw. Eng. Appl., vol. 1, no. 2, pp. 26–34, May 2019, doi: 10.20895/inista.v1i2.50.

R. I. A. Casil, E. D. Dimaunahan, M. E. C. Manamparan, B. G. Nia, and A. A. B. Jr, “A DSP Based Vector Quantized Mel Frequency Cepstrum Coefficients for Speech Recognition,” Inst. Electron. Eng. Philipp. J., vol. 3, no. 1, pp. 1–5, 2014.

F. Tempola, M. Muhammad, and Amal Khairan, “PERBANDINGAN KLASIFIKASI ANTARA KNN DAN NAIVE BAYES PADA PENENTUAN STATUS GUNUNG BERAPI DENGAN K-FOLD CROSS VALIDATION,” J. Teknol. Inf. dan Ilmu Komput., vol. 5, no. 5, 2018.

N. Indriani, E. Rainarli, and K. E. Dewi, “Peringkasan dan Support Vector Machinepada Klasifikasi Dokumen,” J. INFOTEL, vol. 9, no. 4, 2017, doi: https://doi.org/10.20895/infotel.v9i4.

P. Bojarczak and W. Nowakowski, “Squat detection in railway rails using Gabor filter bank, SVM classifier and Genetic Algorithms,” in Proceedings of 2017 15th International Conference on ITS Telecommunications, ITST 2017, 2017, pp. 1–7, doi: 10.1109/ITST.2017.7972229.

S. jin Wang, A. Mathew, Y. Chen, L. feng Xi, L. Ma, and J. Lee, “Empirical analysis of support vector machine ensemble classifiers,” Expert Syst. Appl., vol. 36, no. 3 PART 2, pp. 6466–6476, 2009, doi: 10.1016/j.eswa.2008.07.041.

Bila bermanfaat silahkan share artikel ini

Berikan Komentar Anda terhadap artikel Model Pengenalan Suara Teks Bebas Menggunakan Algoritma Support Vector Machine

Refbacks

  • There are currently no refbacks.


Copyright (c) 2020 JURNAL MEDIA INFORMATIKA BUDIDARMA

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



JURNAL MEDIA INFORMATIKA BUDIDARMA
STMIK Budi Darma
Sekretariat : Jln. Sisingamangaraja No. 338 Telp 061-7875998
email : mib.stmikbd@gmail.com

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