Modeling Vocal Knowledge for Speech Synthesis of Standard Arabic

In this work we present a modeling of speech synthesis based on a text written in Standard Arabic using an expert system, two essentials steps are followed： the construction of the sound corpus and the generation of speech by realizing a transformation of the written form of the text into a synthetic speech （TTS Text to Speech,）. This transformation is done firstly by a POT （phonetic orthographical transcription） of any written Standard Arabic text into his corresponding phonetics sequence, and secondly by the production of the voice signal which corresponds to the chain transcribed. We describe the different steps of conception of the system as well as the results obtained compared to others related works studied to realize TTS system based on Standard Arabic.