An Arabic expert system for voice synthesis

In this paper, an efficient Arabic Expert System for Voice Synthesis, referred to us as AESVS, is proposed. This system, which is based on the Standard Arabic language, consists of 3 phases. The first phase is responsible for the automatic acquisition of human expert knowledge. The acquired knowledge consists of Arabic language pronunciation rules along with the required domain dictionary, to be used by the system. The second phase is concerned with the creation of the sound base that contains the acoustic units needed during the voice generation step. The third phase, which represents the speech synthesis operation, allows the generation of a phonemic sequence for any given word. All words in the input text are converted into their corresponding phonemes sequence by using orthographic phonetic transcription that takes into account their adaptation to the Arabic Language. To ensure this conversion from text to speech, we used approximately 350 predicates created by using the PROLOGUE inference engine, which are stored in a knowledge base that can be used upon request, during both the orthographic–phonetic transcription and the voice generation steps.