• Sujay Nanaware
• Abhijith Nair
• Akruti Dwiivedi

This research presents Inclusive Communication, an AI-driven adaptive sign language recognition system aimed at bridging the communication gap for the Deaf and Mute (D&M) community. By leveraging real-time computer vision and deep learning, the system interprets American Sign Language (ASL) gestures into readable text using only a standard camera—eliminating the need for specialized hardware like sensor gloves or depth cameras. The system architecture employs Media Pipe for landmark detection, and dual Convolutional Neural Networks (CNNs) tailored for left- and right-hand gestures, trained on a custom IndASL-26 dataset designed under diverse Indian conditions. The proposed solution achieves 94.2% real-time accuracy, adapts to individual signing styles, and operates across common devices, making it a scalable, affordable, and inclusive tool. Future enhancements aim to incorporate multi-hand gesture recognition, regional sign languages, and integration with mobile platforms and AR-based feedback systems. This work stands as a significant step toward equitable communication and digital accessibility for the D&M population.

Sign Language Recognition, Deaf and Mute Accessibility, Adaptive Communication, Real-Time Gesture Interpretation, Convolutional Neural Networks (CNN), MediaPipe, Human-Computer Interaction, Inclusive Technology, Assistive Communication Systems, Hand Landmark Detection, Indian Sign Language (ISL), American Sign Language (ASL), AI for Accessibility, Computer Vision, Hidden Markov Models (HMM)

"Inclusive Communication Adaptive Sign Language Interpretation Using AI/ML", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 4, page no.i627-i635, April-2025, Available :http://www.jetir.org/papers/JETIR2504885.pdf

"Inclusive Communication Adaptive Sign Language Interpretation Using AI/ML", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 4, page no. ppi627-i635, April-2025, Available at : http://www.jetir.org/papers/JETIR2504885.pdf