HMM/GMM classification for articulation disorder correction among algerian children

In this paper, we propose an automatic classification 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 the experiments, 20 Arabic words are recorded by a 20 Algerian children, with age range between 4 and 6 years old. Signals are recorded and stored as wave format with 16kHz as sampling rate, 12 Mel Frequency Cepstral Coefficients (MFCC), with their first and second derivates, respectively 3 and 33 are extracted from each signal and used to the training and recognition phases. The proposed system achieved its best accuracy recognition 85.73%, with 58stats HMM when the output function is modelled by a GMM with 8Gaussian components.

[1]  Rafik Djemili,et al.  A combination approach of Gaussian mixture models and support vector machines for speaker identification , 2009, Int. Arab J. Inf. Technol..

[2]  Stan Davis,et al.  Comparison of Parametric Representations for Monosyllabic Word Recognition in Continuously Spoken Se , 1980 .

[3]  Jianping Zeng,et al.  A new distance measure for hidden Markov models , 2010, Expert Syst. Appl..

[4]  Ghulam Muhammad,et al.  Multidirectional regression (MDR)-based features for automatic voice disorder detection. , 2012, Journal of voice : official journal of the Voice Foundation.

[5]  Paul Boersma,et al.  Praat: doing phonetics by computer , 2003 .

[6]  Stefan Gheorghe Pentiuc,et al.  Towards the Optimized Personalized Therapy of Speech Disorders by Data Mining Techniques , 2009, 2009 Fourth International Multi-Conference on Computing in the Global Information Technology.

[7]  S. Selva Nidhyananthan,et al.  Fused Mel Feature sets based Text-Independent Speaker Identification using Gaussian Mixture Model , 2012 .

[8]  Sid-Ahmed Selouani,et al.  Investigating the adaptation of Arabic speech recognition systems to foreign accented speakers , 2010, 10th International Conference on Information Science, Signal Processing and their Applications (ISSPA 2010).

[9]  Abderrahmane Amrouche,et al.  An efficient speech recognition system in adverse conditions using the nonparametric regression , 2010, Eng. Appl. Artif. Intell..

[10]  Slim Abdennadher,et al.  Survey on common Arabic language forms from a speech recognition point of view , 2009 .

[11]  Lotfi Salhi,et al.  Voice Disorders Identification Using Multilayer Neural Network , 2010, Int. Arab J. Inf. Technol..

[12]  Mervat Fashal,et al.  Syllable-based automatic Arabic speech recognition , 2008 .

[13]  Muhammad Ghulam,et al.  Automatic voice disorder classification using vowel formants , 2011, 2011 IEEE International Conference on Multimedia and Expo.