<![CDATA[This research focuses on the development of an Android application that combines Artificial Intelligence (AI) and speech recognition technology to facilitate communication for people with hearing impairments. This application is built using the Flutter framework with the Dart programming language, and is supported by Firebase as a backend and SQLite for local storage. The development model used is the waterfall model, including the stages of needs analysis, design, implementation, testing, and evaluation. The Indonesian voice dataset was obtained from 100 respondents with varying ages and accents to increase the diversity of the training data. The test results show that the application is able to convert voice to text (speech-to-text) with an accuracy rate of at least 85% and a latency of less than 0.5 seconds. The text-to-speech feature can also produce clear and easy-to-understand sounds. In addition, the application is equipped with real-time sign language detection to support communication. Overall, this application is expected to improve communication accessibility for people with hearing impairments and support the realization of digital inclusion in Indonesia.]]>
Copyrights © 2026
