Development of a Two-Way Filipino Sign Language Communication Device

In the Philippines, approximately 70% of the Deaf community uses Filipino Sign Language (FSL) as their primary mode of communication. A significant challenge exists when interacting with hearing individuals who are not proficient in FSL, creating a barrier to effective social and practical exchange.

The study introduced a two-way device powered by a Jetson Nano. It utilizes the MediaPipe framework and an LSTM Deep Learning Model to recognize ten specific dynamic FSL gestures, converting them into audible speech via the Google Text-to-Speech (gTTS) API. Conversely, it translates spoken words back to text using the Google Speech-to-Text (gSTT) API.

Testing involving sixty trials confirmed the prototype's efficacy. The device achieved a 93.33% accuracy rate, surpassing the established 91.11% standard for reliability, demonstrating that technical innovation can effectively bridge the communication gap between deaf-mute and hearing individuals.