Skip to Main Content
The text to speech synthesis quality depends on the naturalness, on the intelligibility of the speech generated and the specific characteristics to the produced voice. These characteristics depend on the techniques and the methods of synthesis, but also on the care taken to prosodic modelling, especially by introducing Intonatif effects on the synthetic speech. Concerning the Arab language, studies in these domains are not enough in progress, so we have to start our investigations. As no commercial speech database was available for Arabic, our first step was to design, record and label the AIS (Arabic Intonatif speech) database, in order to generate prosodic calculation for synthesized sentences.