Speech Recognition Mobile Application for Learning Iqra’ Using PocketSphinx

Nasution, Arbi Haza and Monika, Winda and Masnur, Tengku Waldi Firmansyah (2022) Speech Recognition Mobile Application for Learning Iqra’ Using PocketSphinx. In: International conference on smart computing and cyber security : strategic foresight, security challenges and innovation 2021, 16-17 June, 2021, Online.

WarningThere is a more recent version of this item available.
[img] Text
P9.pdf - Published Version
Download (1MB)
Official URL: https://link.springer.com/chapter/10.1007/978-981-...

Abstract

Learning and reading the Qur'an is compulsory for every Moslem to gain the reward from God. Therefore, an innovation to help people on learning Qur’an fastly and easily is highly needed. Iqra’ is one such way to learn Qur’an by reading the Arabic letters and words. The aim of this study is to create an interactive iqra’ learning media using a smartphone by implementing speech recognition with pocketsphinx framework. The speech processing method applied is Mel Frequency Cepstrum Coefficients and Hidden Markov Model. The speech data are collected by recording the voices of 4 trainers and 2 testers using an audio recorder and the vocab data are gotten by taking a sample of 73 hijaiyah words on the iqra’ level 2 and 3. The result shows that the application can detect testers' voice with just 10.27% and 8.94% decrease in accuracy compared to the trainers' voice for male and female, respectively. The average usability testing of the Mobile Application is 76.67% which means the usability of the mobile phone is quite high.

Item Type: Conference or Workshop Item (Paper)
Subjects: T Technology > T Technology (General)
Divisions: > Teknik Informatika
Depositing User: Monika Winda Monika
Date Deposited: 28 Mar 2023 07:04
Last Modified: 28 Mar 2023 07:04
URI: http://repository.uir.ac.id/id/eprint/21154

Available Versions of this Item

Actions (login required)

View Item View Item
Repository Universitas Islam Riau is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.