Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{198815,
        author = {PRASANTH T and KOWSALYA G and REENA DEVI N and SAJETHA K and SOWMIYA M},
        title = {Speech impaired people communicate to Real-Time Sign Language Detection with Deep Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {10470-10477},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=198815},
        abstract = {People who have problems with their speech frequently face enormous challenges to communicate due to barriers that restrict their ability to communicate in real-time, get important help, and engage in social activities. This project addresses these difficulties by using a real-time hand gesture recognition system based on CNN, which will allow gestures to be converted immediately into both text and audio forms. The system will also recognize a wide variety of gestures and signs, including emergency signs, so that critical communication may occur quickly during emergencies. To assist in making this process available to as many people as possible, the platform will produce multiple outputs in the three major languages spoken in India, making the project useful for users across different language groups. Additionally, the interface displays the corresponding text-based sign symbols, assisting users who are either learning how to sign or interacting with others who do not know how to sign. By combining cutting-edge machine-learning techniques with attention to user-friendly visual and auditory feedback, this system will bring individuals with speech impairments and their communities together socially, thus increasing social interaction, education, and access to public services. In addition, this innovative approach will give users more independence and confidence while increasing the visibility and understanding of sign language, thereby creating a more inclusive and accessible environment for people with speech and communication discrepancies.},
        keywords = {Speech impairment, Sign language recognition, Hand gesture recognition, Convolutional Neural Networks (CNN), Real-time translation, Multilingual support, Assistive technology, Inclusive communication.},
        month = {April},
        }