A Database for Speech Processing Based Qur'anic Recitation Correction
Ahmed Abdullah Alobaylani, Mohammad Tanvir Parvez, Suliman A. Alsuhibany · 2020 International Conference on Computing and Information Technology (ICCIT-1441) · 2020
In this paper, we present a database of Qur'anic recitations for the purpose of automatic speech processing based tajweed correction. To the best of our knowledge, this is the first such database specifically designed to assist the researchers in Qur'anic recitations. A total of 54 different errors made by people while reciting Surah Al-Fatihah are identified. 17 volunteer reciters participated in recording the erroneous recitations for these 54 cases, along with the correct recitations. The resultant data contains over 1000 unique audio samples. All the data samples are labelled for ease of access by the researchers. In addition, some speech level feature analysis is discussed for the database. An interactive recitation learning application is presented to demonstrate the use of the developed database.