Mapping the Landscape of AI-driven Quranic Recitation Recognition: A Bibliometric and Thematic Analysis (2016–2026)

Abstract

This study aims to explore the development and application of artificial intelligence techniques in Arabic speech recognition, with a specific focus on recitation accuracy, pronunciation analysis, and language learning support. It seeks to identify trends, methods, and challenges in AI-based Arabic recitation recognition systems. A bibliometric and systematic review approach was employed using the Scopus database. Relevant publications from 2016 to 2026 were retrieved using a structured query combining keywords related to speech recognition, machine learning, and Arabic language processing. The selected studies were analyzed based on research trends, methodologies, and application domains. The results indicate a growing interest in deep learning approaches such as neural networks, recurrent neural networks (RNN), convolutional neural networks (CNN), and transformer-based models for Arabic speech and recitation recognition. Applications are primarily focused on pronunciation assessment, computer-assisted language learning, and Quranic recitation systems. However, challenges remain in handling dialectal variations, limited annotated datasets, and the complexity of Arabic phonetics. This study is limited to publications indexed in Scopus and may exclude relevant works from other databases. Future research should focus on improving dataset availability, incorporating tajweed rules, and enhancing model robustness for diverse Arabic dialects and recitation styles. This paper provides a comprehensive overview of AI-driven Arabic recitation recognition, highlighting current trends and gaps while offering insights for future research in educational technology and speech processing. Keywords: Arabic speech recognition, recitation recognition, artificial intelligence, deep learning, pronunciation assessment, computer-assisted language learning, bibliometric review.