Feature Extraction Using Mel-Frequency Cepstral Coefficients (MfCC) Technique For A Tajweed Guess Based on Android Application Development

Abstract

The development of information and communication technology today has had a significant impact on various aspects of life, including education. One notable example is the increasing number of applications designed for learning to recite the Quran with proper tartil. The growing trend of tahfidz (Quran memorization) is undoubtedly a positive development from a religious perspective. However, many individuals focus solely on memorization without acquiring the ability to recite the Quran properly and accurately. One discipline that supports proper Quran recitation is the knowledge of tajweed. Numerous applications have been developed in this field, especially on Android platforms. However, applications that utilize artificial intelligence (AI) to recognize tajweed rules and involve users in guessing tajweed readings are still in need of further development. The aim of this research is to develop a tajweed learning application using the concept of Automatic Speech Recognition (ASR). This study employs data collection methods such as literature review, quantitative methods, and testing. The design is represented using Unified Modeling Language (UML), while the application is tested using the Black Box Testing method. For data analysis and testing of the speech recognition model, the Hidden Markov Model (HMM) algorithm is employed, with Mel-Frequency Cepstral Coefficients (MFCC) used for feature extraction. The output of this research is an Android-based tajweed learning application that integrates speech recognition and allows users to guess tajweed rules interactively.