Interactive Learning Tool Using a Neural Network Algorithm for Speech-Delayed Child

Abstract

Interactive Learning Tool using a Neural Network Algorithm for Speech-Delayed Child is a system that was developed mainly for speech-delayed children that utilized a multi-sensory approach and interactive learning technique in assessing the speech disorder. Phonology was focused as the content of the learning tool the lessons are based on the consonant-acquisition chart which contains the rules and system for speech sound production. Speech recognition was implemented to analyze, recognized, and matched the child’s speech to the exact word in the lesson. The system’s functionality is internet based and Google’s voice recognition is implemented to carry out the matching process. Neural Network Algorithm methodology is used to calculate the child’s test result. The application software is developed using HTML, Java, and PHP as the main programming language and Android Studio with Android Developer Tools as the working environment. It uses mySQL in managing its database The software is developed for the android operating system, with the version starting which stored the child’s information and results. The set of lessons is categorized by age namely: AGES 3-4, AGES 4-5, AGES 5-6, and AGES 6-7. Each category has a unique set of lessons categorized by: syllables with 67 lessons, words with 57 lessons, and phrases which contains 26 lessons. When the user finishes all the lessons prepared the system will generate the result, and the submit button transfers the data result into the teachers’ record in a separate system installed on a desktop/laptop computer.