Genetic supervised classification of Standard Arabic fricative sounds

Abstract

The purpose of this paper is the application of the Genetic Algorithms (GAs) to the supervised classification level, in order to recognize Standard Arabic (SA) fricative consonants of continuous, naturally spoken, speech. We have used GAs because of their advantages in resolving complicated optimization problems where analytic methods fail. For that, we have analyzed a corpus that contains several sentences composed of the thirteen types of fricative consonants in the initial, medium and final positions, recorded by several male Jordanian speakers. Nearly all the world's languages contain at least one fricative sound. The SA language occupies a rather exceptional position in that nearly half of its consonants are fricatives and nearly half of fricative inventory is situated far back in the uvular, pharyngeal and glottal areas. We have used Mel-Frequency Cepstral analysis method to extract vocal tract coefficients from the speech signal. Among a set of classifiers like Bayesian, likelihood and distance classifier, we have used the distance one. It is based on the classification measure criterion. So, we formulate the supervised classification as a function optimization problem and we have used the decision rule Mahalanobis distance as the fitness function for the GA evaluation. We report promising results with a classification recognition accuracy of 82%.M. Aissiou ( ) · M. Guerti Algiers National Polytechnique School, BP 182, El-Harrach,

Recognition of isolated digits using DNN–HMM and harmonic noise model

“…The difference between short and long vowels is roughly double or more in time duration. The relative length of a short vowel is about 100–150 ms, while that of a long one is between 225 and 350 ms [29].…”

Prosody Modification of Standard Arabic Speech Using Combining Synchronous Overlap and Add With Fixed-Synthesis Algorithm and Multi Level Discrete Wavelet Transform

“…The SA is composed of twenty eight phonetically distinct consonants phonemes, 3 short vowels (a, u, i) which contrast phonetically with their long counterparts (a:, u:, i:) and six corresponding variants of the short and the long vowels in emphatic context (Aissiou and Guerti, 2009). The silence in SA is called (suku:n).…”

“…The phonetic frame work in this study is that of the International Phonetic Alphabet (IPA) as used within the California University Phonological Segment Inventory Database (UPSID) (Aissiou and Guerti, 2009).…”

“…The entire Arabic consonants can be geminated except the glottal stop consonant [?] (Aissiou and Guerti, 2009).…”

“…Many techniques were reported in the literature for automatic sound classification (Aissiou and Guerti, 2009;Johnson, 1996). The voiced/unvoiced classifications have proved to be well suitable for real time application.…”