XGBoost and Convolutional Neural Network Classification Models on Pronunciation of Hijaiyah Letters According to Sanad

Abstract

According to Sanad (reading designation), the pronunciation of Hijaiyah (basics of word and sentence formation in Arabic) letters can serve as a benchmark for correct or valid reading based on the makhraj (the place where the letters come out when they are pronounced) and phonetic properties of the letters. However, a scarcity of qualified Qur'anic Sanad teachers poses a significant challenge to effective Qur’an learning. This study aims to identify the most practical combination of classification models in constructing a voice recognition system that facilitates Qur’an learning direct teacher interaction. The method used in this research include the XGBoost algorithm and CNN. This research found that the CNN model was employed for 10 out of 12 phonetic property labels, with XGBoost model applied to the remaining two. Furthermore, the inclusion of additional data yielded performance results for each property, with an average accuracy of 78.14% for property S (letters with opposing properties), 70.69% for property T (letters without opposing properties), and an overall average of 73.79% per letter.