Computer speech recognition to text for recite Holy Quran

3rd Annual Applied Science and Engineering Conference

工业技术;自然科学

Gerhana, Y.A.^1 ; Atmadja, A.R.^2 ; Maylawati, D.S.^2 ; Rahman, A.^1 ; Nufus, K.^1 ; Qodim, H.^3 ; Busr^3 ; Ramdhani, M.A.^1

Departement of Informatics, UIN Sunan Gunung Djati Bandung, Jalan A H Nasution 105, Bandung

40614, Indonesia^1

Departement of Informatics, Sekolah Tinggi Teknologi Garut, Jalan Mayor Syamsu No 1, Tarogong Kidul Kabupaten, Garut

44151, Indonesia^2

Faculty of Ushuluddin, UIN Sunan Gunung Djati Bandung, Jalan A H Nasution 105, Bandung

40614, Indonesia^3

关键词: Arabic texts;    Computer speech recognition;    Distance algorithm;    Holy quran;    Muslims;    Shuffle algorithms;    Text-matching;    Winkler;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/434/1/012044/pdf
DOI  :  10.1088/1757-899X/434/1/012044

来源: IOP

【 摘 要 】

Memorizing Holy Quran or Tahfidz is important to worship for Muslim around the world. This research proposed a solution in memorizing and learning Holy Quran easily. To help in remembering the sentence of Holy Quran, Fisher-Yates Shuffle had implemented for randomization of the letter of the Holy Quran. In this research, the sound of Holy Quran had recorded and it was converted into Arabic text to recognize the character of text. Jaro-Winkler was used for text matching algorithm, and Google Speech API help to define speech recognition. The result showed that Fisher-Yates Shuffle Algorithm was successfully applied in randomization with 15 times of experiments. And also, Jaro-Winkler Distance algorithm had performed well as text matching between text from speech recognition and Holy Quran text. The result showed that the percentage of accuracy was around 91% and an average of matching time was 1.9 ms.