Classification of emphatic consonants and their counterparts in Modern Standard Arabic using neural networks

This paper presents the work of acoustic analysis related to Modern Standard Arabic (MSA). The problem of classifying the consonant counterparts in MSA is tackled here. The study considers four phonemes: /dς, ∂ς/ and their non-emphatic counterparts /d, ∂ς/ respectively. An accurate automatic classification for those phonemes is to be achieved. Artificial neural networks (ANNs) are used for that purpose. The multilayer perceptron (MLP) is applied to the features extracted from the speech signals. The speech utterances used in this study are from KAPD database. Classification accuracy of 83.9% was achieved.

[1]  Y. A. Alotaibi,et al.  Effect of Arabic emphaticness on Voice O\NET Time (VOT) , 2012, 2012 International Conference on Audio, Language and Image Processing.

[2]  T. Baer,et al.  The Emphatic and Pharyngeal Sounds in Hebrew and in Arabic , 1988, Language and speech.

[3]  Douglas D. O'Shaughnessy,et al.  Experiments on Automatic Recognition of Nonnative Arabic Speech , 2008, EURASIP J. Audio Speech Music. Process..

[4]  S.-A. Selouani,et al.  Investigating Automatic Recognition of Non-Native Arabic Speech , 2007, 2007 Innovations in Information Technologies (IIT).

[5]  Yousef Ajami Alotaibi,et al.  Is it a specific vocal tract shape in order to pronounce emphatics? , 2010, 2010 7th International Symposium on Communication Systems, Networks & Digital Signal Processing (CSNDSP 2010).

[6]  John H. L. Hansen,et al.  Discrete-Time Processing of Speech Signals , 1993 .

[7]  Allard Jongman,et al.  Acoustic Correlates of Emphasis in Jordanian Arabic: Preliminary Results , 2003 .

[8]  Mansour M. Alghmadi,et al.  KACST Arabic Phonetics Database , 2003 .

[9]  M. A. Romli,et al.  Speech quality based on Arabic pronunciation using MFCC and LDA: Investigating the emphatic consonants , 2012, 2012 IEEE International Conference on Control System, Computing and Engineering.

[10]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[11]  A. H. Kandil,et al.  Automatic detection for some common pronunciation mistakes applied to chosen Quran sounds , 2010, 2010 5th Cairo International Biomedical Engineering Conference.