In this paper, we propose an automatic classificati on for Arabic phonemic substitution using a Hidden Markov Model/Gaussian Mixture Model (HMM/GMM) systems. The main objective is to help Algerian children in the correction of articulation problems. Five cases are analyzed in t he experiments, 20 Arabic words are recorded by a 2 0 Algerian children, with age range between 4 and 6 years old. Signals a re recorded and stored as wave format with 16kHz as sampling rate, 12 Mel Frequency Cepstral Coefficients (MFCC), with th eir first and second derivates, respectively 3 and 33 are extracted from each signal and used to the training and recognitio n phases. The proposed system achieved its best acc uracy recognition 85.73%, with 58stats HMM when the output function i s modelled by a GMM with 8Gaussian components.

[1] Abed A. and Guerti M., Apllication Des HMM A La Substitution Phon mique Dans l'Arabe Parl , Journ es d'Etudes Alg ro8Fran aises de Doctorants en Signal8Image and Applications , pp. 18-23, Algeria, 2012.

[2] Abed A. and Guerti M., Errors Classification of Phonemic Substitution in Arabic Speech, in Proceedings of the International Congress on Telecommunication and Application 14 , Bejaia, Algeria, pp. 23-24, 2014.

[3] Alotaibi Y. and Selouani S., Investigating the Adaptation of Arabic Speech Recognition Systems to Foreign Accented Speakers, in Proceedings of the 10 th International Conference on Information Science , Signal Processing and their Applications , Kuala Lumpur, pp. 646-649, 2010.

[4] Amrouche A., Debyeche M., Ahmed A., Rouvaen J., and Yagoub M., An Efficient Speech Recognition Systemin Adverse Conditions Using the Nonparametric Regression, Engineering Applications of Artificial Intelligence , vol. 23, no. 1, pp. 85-94, 2010.

[5] Azmi M. and Tolba H., Syllable-Based Automatic Arabic Speech Recognition in Different Condition of Noise, in Proceedings of the 9 th International Conference on Signal Processing , Beijing, pp. 601-604, 2008.

[6] Danubianu M., Pentiuc S., and Socaciu T., Towards the Optimized Personalized Therapy of Speech Disorders by Data Mining Techniques, in Proceedings of the 4 th International Multi8 Conference on Computing in the Global Information Technology , Cannes, pp. 20-25, 2009.

[7] Davis S. and Mermelstein P., Comparison of Parametric Representations for Monosyllabic Word Recognition in Continuously Spoken Sentences, IEEE Transaction on Acoustics, Speech and Signal Processing , vol. 28, no. 4, pp. 357-366, 1980.

[8] Djemili R., Bourouba H., and Korba A., A Combination Approach of Gaussian Mixture Models and Support Vector Machines for Speaker Identification, the International Arab Journal of Information Technology , vol. 6, no. 5, pp. 490-489, 2009.

[9] Elmahdy M., Gruhn R., Minker W., and Abdennadher S., Survey On Common Arabic Language Forms From Speech Recognition Point of View, in Proceedings of International Conference on Acoustics , pp. 63-66, 2009.

[10] Fisher W., Doddington G., and Goudie-Marshall K., The DARPA Speech Recognition Research Database: Specifications and Status, in Proceedings of the DARPA Speech Recognition Workshop , pp. 93-100, 1986.

[11] Kumari R., Nidhyananthan S., and Anand G., Fused Mel Feature Sets Based Text-Independent Speaker Identification Using Gaussian Mixture Model, Procedia Engineering , vol. 30, pp. 319- 326, 2012.

[12] Muhammad G., AlSulaiman M., Mahmood A., and Ali Z., Automatic Voice Disorder Classification using Vowel Formants, in Proceedings of IEEE International Conference on Multimedia and Expo (ICME) , Barcelona, pp.1-6, 2011.

[13] Muhammad G., Mesallam T., Malki K., Farahat M., Mahmood A., and Alsulaiman M., Multidirectional Regression (Mdr)-Based Features For Automatic Voice Disorder Detection, Journal of Voice , vol. 26, no. 6, pp. 817.e19-817.e27, 2012.

[14] Praat: doing Phonetics by Computer., available at: http://www.fon.hum.uva.nl/praat, last visited 2014.

[15] Salhi L., Mourad T., and Cherif A., Voice Disorders Identification Using Multilayer Neural Network, the International Arab Journal of Information Technology , vol. 7, no. 2, pp. 177- 185, 2010.

[16] Zeng J., Duan J., and Wu C., A New Distance Measure for Hidden Markov Models, Expert Systems with Applications , vol. 37, no. 2, pp. 1550-1555, 2010.