Holy Qur'an speech recognition system distinguishing the type of recitation

Abstract

The act of reading Qur'an and pronouncing its sound dwells on the type of recitation. These are referring to the recitation of Warsh or the recitation of Hafss. It's very important to recognise the type of recitations, especially with the diversity and the spread of Qira'at in the world. This research presents a speech recognition system that distinguishes between the different types of the Qur'an recitation. The aim here is to design and developed a speech recognition for recitation of the Holy Qur'an for detecting the types of recitations and correction of fundamental and general errors. Although, there are several analysers that have been examined for error corrections, unfortunately, these analysers were not suitable for the act of recitation of the Holy Qur'an. Thus, the proposed system will be capable to recognize, identify and point out any mismatch. An experiment among student recitation with the recitation made by the expert teachers stored in a database has been done. Mel-Frequency Cepstral Coefficient (MFCC) for feature extraction and Hidden Markov Models (HMM) for feature classification are used.