Application of HMM and Substitution Phonemic
|
10.5120/15833-4714 |
Bouamama Rda Sadouki, Abed Ahcne and Mouhamed Djebbouri. Article: Application of HMM and Substitution Phonemic. International Journal of Computer Applications 90(19):43-47, March 2014. Published by Foundation of Computer Science, New York, USA. BibTeX
@article{key:article,
author = {Bouamama Rda Sadouki and Abed Ahcne and Mouhamed Djebbouri},
title = {Article: Application of HMM and Substitution Phonemic},
journal = {International Journal of Computer Applications},
year = {2014},
volume = {90},
number = {19},
pages = {43-47},
month = {March},
note = {Published by Foundation of Computer Science, New York, USA}
}
Abstract
The performances of an automatic system of recognition of word are, generally, directly related to quality, the type and the quantity of the data of training. This article shows the effect like the speaker on the performances of a system of recognition of the words isolated directed towards the problem from pathology from the spoken Arabic, in particular, substitution of the spoken Arabic. The system suggested is based on the models of markov hidden (HMM) whose exit is modeled by a density multigaussiennes (GMM). For the representation of the signals of word coefficients (MFCC) are used.
References
- M. Alkhouli, “Alaswaat Alaghawaiyah,” Daar Alfalah, Jordan 1990.
- L. E. Baum, “An inequality and associated maximization technique in statistical estimation for probabilistic functions of Markov processes,” Inequalities, vol. 3, pp. 1-8, 1972.
- L. E. Baum, T. Petri, G. Soules and N. Weiss, “A maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains, ” Annals in Mathematical Statistics, vol. 41, pp. 164-171, 1970.
- Z.A. Benselama, M. Guerti and M.A. Bencherif, “Arabic Speech Pathology Therapy Computer Aided System,” Journal of Computer Science 3 (9), pp. 685-692, 2007.
- J.A. Bilmes, “A gentle Tutorial of the EM Algorithem and its applications to Parametre Estimation for Gaussian Mixture and Hidden Markov Models, ” Technical report, ICSI-TR-97-021, 1998.
- M. Elshafei, “ Toward an Arabic Text-to -Speech System', The Arabian Journal for Science and Engineering, ” 16(4B): , ,pp.565-83, Oct 1991.
- A. Eshajhse, “Articulation and speech disorders: types, treatment and diagnostic, ” Saudi Arabia, limited golden papers. 1997.
- G. D.Forney, “The Viterbi algorithm, ” IEEE Proceedings,vol. 61, pp. 268-278, March 1973.
- HTK3 2004 HTK3, “ Hidden Markov Model Toolkit, ” Technical report, Cambridge University, http://htk.eng.cam.ac.uk/
- L. B. Jackson, “ Digital filters and signal processing,” New York: Kluwer Academic Publishers, 1996.
- S. E. Levinson, L. R. Rabiner and M. M Sondhi, “An introduction to the application of the theory of probabilistic functions of a Markov process to automatic speech recognition,” Bell System Technical Journal, vol. 62, no. 4, pp. 1035-1074, 1983.
- P. Lockwood, C. Baillargeat, J. Gillot, J. Boudy and G. Faucon, “ Noise reduction for speech enhancement in cars: non linear spectral subtraction,” Proc. Eurospeech 91. Genova, Italia, 1991.
- L. Rabiner and B. Juang, “ Fundamentals of Speech Recognition,” Prentice-Hall, 1993.
- A. J. Viterbi, “ Error bounds for convolutional codes and an asymptotically optimal decoding Aalgorithm, ” IEEE Transactions on Information Theory, vol. IT-13, pp. 260-269, April 1967.