Amanu: CNN-RNN Kapampangan Language Learning-Based System for Grade School Learners

This study examines the development and implementation of "Amanu", a deep learning-based computer system designed to enhance Kapampangan language acquisition among grade school learners. Utilizing a CNN-RNN architecture, the system addresses challenges in preserving and promoting the Kapampangan language. The research employed a quantitative descriptive approach, using ISO 25010-based surveys for data collection. Developed using Agile methodology, Amanu incorporates features such as a pronunciation checker, multimedia lessons, interactive games, and a comprehensive dictionary. Findings indicate that Amanu significantly aids both teachers and learners in Kapampangan language education, receiving high ratings across all ISO 25010 categories with an overall mean score of 3.80. The study concludes that integrating such systems into standard teaching methods can revolutionize language learning approaches, making Kapampangan acquisition more accessible and engaging. Recommendations include incorporating adaptive learning algorithms and expanding cultural content. This research contributes to the fields of educational technology and language preservation, demonstrating the potential of deep learning-based systems in supporting the education of endangered languages.