SIGNSPEAK: Integrating Computer Vision and Speech Synthesis for Alphabet Filipino Sign Language (FSL)

In our interconnected world, effective communication is a fundamental human right fostering social interaction, education, and personal growth. However, individuals with sensory impairments, such as hearing loss, encounter significant barriers in communication, hindering their participation in society. This challenge is pronounced in the Philippines, where Filipino Sign Language (FSL) is vital for the Deaf community. The “SignSpeak” study addresses these challenges by integrating computer vision and speech synthesis technologies. Utilizing platforms like Raspberry Pi and Jetson Nano, SignSpeak interprets hand gestures in real-time, converting them into audible speech, and translates spoken language into text, enabling bidirectional communication. This approach empowers individuals with varying sensory abilities, fostering inclusivity and enhancing educational opportunities. SignSpeak promotes social equity and empowers the Deaf community in the Philippines through rigorous software and hardware development and a commitment to linguistic inclusivity. Beyond technical innovations, SignSpeak envisions a future where individuals of all abilities can communicate freely and participate in society. The study results were highly successful, demonstrating 95% accuracy, 96% precision, 94% recall, and a 95% F1 score. Additionally, the prototype received positive feedback, with an overall mean score of 4.845. These outcomes highlight SignSpeak's effectiveness and potential impact in improving communication accessibility for the Deaf community in the Philippines.