What question did this study set out to answer?

To address communication barriers faced by hearing and speech-impaired individuals by developing a bidirectional ISL translation system.

February 5, 2026Open Access

SignBridge: An Offline Bidirectional Indian Sign Language Translation System

Key Points

To address communication barriers faced by hearing and speech-impaired individuals by developing a bidirectional ISL translation system.
Developed an offline system for Sign-to-Text/Speech and Text-to-Sign translation.
Utilized MediaPipe for extracting hand and pose landmarks.
Employed a hybrid CNN–Transformer model for gesture recognition.
Implemented a full-stack solution with React.js and Flask for user interaction.
Incorporated an avatar-based module for visual sign outputs.
Successfully demonstrated real-time bidirectional translation between signed and textual forms.
Achieved significant improvements in gesture recognition accuracy.
Designed the system to function effectively in low-resource environments.

Abstract

Communication barriers persist for hearing and speech-impaired individuals due to the lack of real-time, offline, bidirectional Indian Sign Language (ISL) translation tools. This paper presents SignBridge, an offline bidirectional system supporting Sign-to-Text/Speech and Text-to-Sign translation. MediaPipe is used for extracting hand and pose landmarks, while a TensorFlow-based hybrid CNN– Transformer model performs dynamic gesture recognition. A full-stack implementation using React.js and Flask ensures real-time interaction, and an avatar-based rendering module generates visual sign outputs. The system is designed for low- resource environments with improved privacy and reduced dependency on internet connectivity.

Read Full Paperexternally

اسأل الذكاء الاصطناعي

Bookmark

View Full Paper