Phonetic Study for Automatie Recognition of Arabic

We propose in this paper a phonetic study of stan dard Arabic based essentielly on the spectrographic visions of 50 sentences of the DJOUMA corpus we have constituted. This study allowed us to determine the pertinent parameters of continuous speech recog nition. For the recognition part, we present the algo rithms developed and the results obtained for three important questions: The segmentation of speech into gross phonetic classes. This process is based· on methodes adapted from the The detection of plosives and fricatives. Results obtained on speech pronounced by 5 different speakers are presented and discussed, together with preliminary results for recognition of Arabic conso nants.