ALGORITMA PENGHAPUS DERAU/SILENCE DAN PENENTUAN ENDPOINT DENGAN NILAI AMBANG TERBOBOT UNTUK SINYAL SUARA
Keywords:
Automatic Speeh Recognition, silence remover, endpoint detection, weighted value
Abstract
In automatic speech recognition, the accuracy of recognition depends on the accuracy of endpoint detection of speech signal. There are several methods commonly used, such as short time energy-zero crossing rate, statistics and hybrid. However, these methods have limitations in determining the threshold value, the range of methods and computational efficiency. Therefore, we need a method that can solve these problems one of them by modifying the threshold value. The threshold value is modified such that its value increase four time from its initial value after multiplied by the weight. The results shows this novel method provides high accuracy on silence remover and end point detection although some data were missing.
References
[1] J. Ramirez, J. Górriz, and J. Segura, “Voice activity detection. fundamentals and speech recognition system robustness,” Robust Speech Recognit. …, no. June, pp. 1–22, 2007.
[2] S. S. G. Saha, Sandipan Chakroborty, “A New Silence Removal and Endpoint Detection Algorithm for Speech and Speaker Recognition Applications,” in IEEE 11th National Conference on Communications (NCC), 2005, pp. 291–195.
[3] L. F. Lamel, L. R. Rabiner, A. E. Rosenberg, and J. G. Wilpon, “Improved endpoint detector for isolated word recognition,” IEEE Trans. Acoust., vol. ASSP-29, no. 4, pp. 777–785, 1981.
[4] R. Asliyan, “Syllable Based Speech Recognition,” in Speech Technology, I. Ipsic, Ed. InTech, 2011, pp. 263–284.
[5] X. Huang, A. Acero, and H.-W. Hon, Spoken Language Processing: A Guide to Theory, Algorithm and System Development. Prentice Hall, 2001.
[6] L. R. Rabiner and M. R. Sambur, “An Algorithm for Determining the Endpoints of Isolated Utterances,” Bell Syst. Tech. J., vol. 54, no. 2, pp. 297–315, 1975.
[7] D. Jurafsky and J. H. Martin, Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition. Prentice Hall, 2008.
[8] L. Gu and S. A. Zahorian, “A new robust algorithm for isolated word endpoint detection,” Energy, vol. 1, no. 1. pp. 1–4, 2002.
[9] Abriyono and A. Harjoko, “Pengenalan Ucapan Suku Kata Bahasa Lisan Menggunakan Ciri LPC, MFCC, dan JST,” IJCCS, vol. 6, no. 2, pp. 23–34, 2012.
[10]I. McLoughlin, Applied Speech And Audio Processing : With Matlab Examples, 1st ed. United Kingdom: Cambridge University Press, 2009.
[2] S. S. G. Saha, Sandipan Chakroborty, “A New Silence Removal and Endpoint Detection Algorithm for Speech and Speaker Recognition Applications,” in IEEE 11th National Conference on Communications (NCC), 2005, pp. 291–195.
[3] L. F. Lamel, L. R. Rabiner, A. E. Rosenberg, and J. G. Wilpon, “Improved endpoint detector for isolated word recognition,” IEEE Trans. Acoust., vol. ASSP-29, no. 4, pp. 777–785, 1981.
[4] R. Asliyan, “Syllable Based Speech Recognition,” in Speech Technology, I. Ipsic, Ed. InTech, 2011, pp. 263–284.
[5] X. Huang, A. Acero, and H.-W. Hon, Spoken Language Processing: A Guide to Theory, Algorithm and System Development. Prentice Hall, 2001.
[6] L. R. Rabiner and M. R. Sambur, “An Algorithm for Determining the Endpoints of Isolated Utterances,” Bell Syst. Tech. J., vol. 54, no. 2, pp. 297–315, 1975.
[7] D. Jurafsky and J. H. Martin, Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition. Prentice Hall, 2008.
[8] L. Gu and S. A. Zahorian, “A new robust algorithm for isolated word endpoint detection,” Energy, vol. 1, no. 1. pp. 1–4, 2002.
[9] Abriyono and A. Harjoko, “Pengenalan Ucapan Suku Kata Bahasa Lisan Menggunakan Ciri LPC, MFCC, dan JST,” IJCCS, vol. 6, no. 2, pp. 23–34, 2012.
[10]I. McLoughlin, Applied Speech And Audio Processing : With Matlab Examples, 1st ed. United Kingdom: Cambridge University Press, 2009.
