SySRA: A System of a Continuous Speech Recognition in Arab Language

Authors: Samir Abdelhamid, Noureddine Bouguechal

Abstract:

We report in this paper the model adopted by our system of continuous speech recognition in Arab language SySRA and the results obtained until now. This system uses the database Arabdic-10 which is a corpus of word for the Arab language and which was manually segmented. Phonetic decoding is represented by an expert system where the knowledge base is translated in the form of production rules. This expert system transforms a vocal signal into a phonetic lattice. The higher level of the system takes care of the recognition of the lattice thus obtained by deferring it in the form of written sentences (orthographical Form). This level contains initially the lexical analyzer which is not other than the module of recognition. We subjected this analyzer to a set of spectrograms obtained by dictating a score of sentences in Arab language. The rate of recognition of these sentences is about 70% which is, to our knowledge, the best result for the recognition of the Arab language. The test set consists of twenty sentences from four speakers not having taken part in the training.

Keywords: Continuous speech recognition, lexical analyzer, phonetic decoding, phonetic lattice, vocal signal.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1071426

References:

[1] Young, S.J. and al, multilingual vocabulary speech recognition, Compuet Speech and Language 0-73-89-0, 1997.
[2] J.P. Haton, D. Fohr et M. Djoudi : Un système expert pour le décodage acoustico-phonétique pour l-Arabe standard. Conférence Maghrébine, Septembre 1989.
[3] Y. Belkaid : Les voyelles de l-Arabe littéraire moderne. Analyse spectrographique Rapport N┬░ 16, travaux de l-institut de phonétique de Strasbourg, 1984.
[4] O. Deroo, C. Ris: Hybrid HMM/ANN Systems speaker independent continuous speech recognition in French. Travaux de l-école Polytechnique de MONS Belgique, 2000.
[5] S. Abdelhamid : Contributions ├á l-étude et ├á la réalisation d-une machine ├á dicter en Fran├ºais. Thèse de Magister de l-institut d-informatique de l-université de Batna, Algérie, 1994.
[6] M. Djoudi ET J.P. Haton: The SAPHA Acoustic Phonetic Decoder System for standard Arabic. International conference on spoken language processing, 1990.
[7] M. Guerti : Contribution ├á la synthèse de la parole en Arabe standard. Actes des 16ème journées d-études sur la parole. Hammamet, Tunisie 1987.
[8] A. Giannini et M. Petorino. The Emphatic Consonants in Arabic. Giadini Editori, 1982.
[9] Benhamouda : Morphologie et syntaxe de la langue Arabe. Nationale Edition, 1983.
[10] N. Carbonell, J. P. Haton, D. Fohr. Aphodex: design and implementation of an acoustic phonetic decoding expert system. IEEE: International conference on Acoustics, speech and signal processing, 1986.
[11] V. Barreaud : Reconnaissance automatique de la parole continue: compensation des bruits par transformation de la parole. Thèse de l-université de Nancy1, 2004.