Brylle Miguel E. Andres
1 Publications
Scopus ID: 105030206133
2024 IEEE 16th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM), (2025), pp. 1-6
Conference Paper | Published: December 3, 2025
Abstract
This study centers on the essential role played by Speech-Language Pathologists (SLPs) in the diagnosis and treatment of speech and language disorders within the Philippines. It underscores the significant difficulties resulting from the limited availability and effectiveness of Augmentative and Alternative Communication (AAC) tools, particularly in the context of the Filipino language. These limitations impede the progress of Filipino children struggling with speech delay disorders. The study aims to develop AAC software integrated with an intelligent tutoring system in Filipino. This innovative approach incorporates Filipino AAC tools such as AAC boards, assessments, client management, and identification of rapidguessing behavior on AAC assessments on different difficulty levels using a decision tree algorithm, providing a structured and personalized therapy approach. The software was evaluated using FURPS with a total of 50 participants, whom are the 30 or 60 % speech-language pathologists, 8 or 16 % Information Technology and Computer Science (IT/CS) professionals, 2 or 4 % CS Professors, and 10 or 20 % Parents/Guardians. The computed Cronbach's alpha (α
) was 0.95 which indicates the FURPS instrument has excellent internal consistency. The grand mean of the software evaluation was rated at 4.63 which highlights the generally positive evaluation of the system. Precision, recall and F1-score assess the model's performance in binary classification. For the class labeled “0,” the model achieved a precision of 0.99, a recall of 1, and an F1 score of 0.99. This indicates that the model has high accuracy in predicting instances belonging to class “0.” For the class labeled “1,” the model achieved a precision of 0.95, a recall of 0.92, and an F1-score of 0.93, indicating slightly lower performance than class “0.” The findings of this study and the developed software have significant implications in the field of AAC. Additionally, this study's contribution serves as a foundation for future advancements in AAC-related technologies, driving innovation and improvement in the field.
) was 0.95 which indicates the FURPS instrument has excellent internal consistency. The grand mean of the software evaluation was rated at 4.63 which highlights the generally positive evaluation of the system. Precision, recall and F1-score assess the model's performance in binary classification. For the class labeled “0,” the model achieved a precision of 0.99, a recall of 1, and an F1 score of 0.99. This indicates that the model has high accuracy in predicting instances belonging to class “0.” For the class labeled “1,” the model achieved a precision of 0.95, a recall of 0.92, and an F1-score of 0.93, indicating slightly lower performance than class “0.” The findings of this study and the developed software have significant implications in the field of AAC. Additionally, this study's contribution serves as a foundation for future advancements in AAC-related technologies, driving innovation and improvement in the field.