Problem Statement: Current algorithms for the recognition and synthesis of Arabic prosody concentrate on identifying the primary stressed syllable of accented words on the basis of fundamental frequency. Generally, the three acoustic parameters used in prosody are: Fundamental frequency, duration and energy. Approach: In this study, we exploited the acoustic parameter of energy by means of a classification by a discriminant analysis to detect the primary accented syllables of Standard Arabic words with the structure [CVCVCV] read by four native speakers (two male and two female). Results: We obtained a percentage of detection equal to 78% of the accented syllables. Conclusion: These preliminary results need to be tested on larger corpora but our results suggest this could be a useful addition to existing algorithms, in the goal of improving systems of automatic synthesis and recognition in Standard Arabic.