Bridging Silence: A Framework for Recognizing and Converting Indian Sign Language to Speech
Jyothika K Raju, Divya A Kittur, Divya Maithreyi Tenneti, M R Anala · 2025
Sign language is a complex visual language that relies on hand gestures, body movements, and facial expressions to communicate meaning. However, the lack of understanding and interpretation of these gestures by individuals who do not use sign language creates a significant communication barrier for deaf and hard-of-hearing individuals. This paper presents a real-time system for recognizing and converting Indian Sign Language (ISL) gestures into speech to bridge this communication gap and enhance accessibility. The system achieves accurate and efficient recognition of ISL gestures in real-time by employing a custom ISL dataset, hand tracking using MediaPipe Hands, and a Random Forest classifier. The model is trained on a diverse set of hand gestures representing alphabets, words, and numbers, created uniquely due to the absence of existing ISL datasets. This project not only addresses critical gaps in existing research related to ISL recognition but also provides a practical solution that can be expanded to include more complex gestures and expressions in the future. This technology has the potential to improve educational and employment opportunities, enhance social interactions, and increase access to services for the deaf and hard-of-hearing community in India, ultimately promoting greater inclusivity and understanding in society.