Communication is a basic human right, yet millions of people in the deaf and hard-of-hearing community face barriers every day—especially in virtual spaces, education, and public services.
As a passionate developer and advocate for inclusive technology, I created SignBridge, an AI-powered system designed to bridge this gap by translating American Sign Language (ASL) into spoken language and vice versa in real time. What began as a local prototype has now grown into a complete solution that can be integrated into modern communication tools like Zoom, Google Meet, or Microsoft Teams—making digital conversations truly accessible.
SignBridge uses a dual-frame video interface:
Frame 1 (Special User): Detects ASL signs using OpenCV and MediaPipe for real-time hand tracking and gesture recognition. The system interprets signs (letters, numbers, phrases) and displays the translated message in the other user's frame.
Frame 2 (Normal User): Uses speech recognition to convert spoken language into text, and then displays a corresponding ASL image or animation so the deaf/hard-of-hearing user can understand the message visually.
All of this is powered by a deep learning model trained on a public Kaggle ASL dataset, which ensures recognition of the full ASL alphabet, common numbers, and key phrases.
Key Features
Real-time ASL hand sign detection using MediaPipe + OpenCV
Voice-to-ASL image translation using speech recognition
ASL alphabet, numbers, and basic phrase recognition
Dual-frame interface for bidirectional communication
Backend REST API to power web and mobile platforms
Future support for integration with Zoom, Meet, and Teams
Cross-platform design: currently building a web app and mobile app
Screenshots / Demos
Get Involved
Want to help make communication more inclusive? Here's how you can contribute:
Test the beta version on web or mobile (coming soon)
Suggest improvements or new features (e.g., gesture training, multilingual support)
Raise awareness about accessibility in tech
Feel free to reach out if you're interested in collaboration, testing, or integration ideas.