Abstract:
The Arabic language is one of the most popular languages due to the number of Arab people and due to its religious status, which makes non-Arabs interested in learning it. However, there are not many speech recognition systems for the Arabic language, or there is no integrated system for it. Because of its extensive vocabulary and morphology, it is more difficult to develop systems to recognize it. For some of these reasons, it uses agglutinative letters and diacritics (الحركات). The Qaidah Noraniah language model was designed to help solve some of these problems. The model was trained with a half hour of data using the CMU Sphinx program, and the model was tested by dependent and independent speakers. The model achieved good results in recognizing single letters, recognizing letters with diacritics and the ability to differentiate between different diacritics of a single letter, as well as recognizing words not used in training where they consisted of letters used in training. The model achieved a letter recognition rate of 67.17%.
