Bridging Communication Gaps: Real-Time Sign Language Detection Platform

Abstract

This paper adopts an interdisciplinary methodology that mixes digital education with disability theory to examine disabled children\'s digital use practices for educational purposes. Research indicates that children\'s lives have been revolutionized through interaction with digital technologies, i.e., computers, laptops and mobile phones. Nevertheless, empirical research on disabled children\'s uses of technology is still in its infancy, especially research that incorporates disabledown opinions in context. As a reply, an exploratory, participatory research investigation was undertaken with the aim to learn about up-to-date, visually impaired children, as a case study in point, having used digital technology for learning, in the situation of inclusive education policy. Disabled children and staff were interviewed in English mainstream schools; data were analyzed based on social practice theory to outline digital use practices defined as digital learning and digital accessibility practices in addition to children\'s experiences. Findings were mixed. Children perceived advantages in utilizing digital technology, specifically tablets, for educational purposes. However, digital accessibility practices were possibly stigmatizing and had an added task burden to overcome difficulties that arose when teachers had not established inclusive digital pedagogy. The paper addresses the implications of these findings and urges more research to lead schools to utilize digital technology to facilitate inclusion.

Introduction

The text discusses the importance of ensuring children with disabilities have equal opportunities to participate in society, particularly through integrating digital technology in education. While technology like computers and mobile devices have transformed learning and social interaction for many children, research focusing specifically on how children with disabilities use digital tools in their daily lives is limited.

The motivation section defines key terms such as Technology Enhanced Learning (TEL), ICT, and gamification, highlighting their roles in supporting children with special needs. Research shows serious games and tailored software can effectively motivate and improve learning, especially for children with intellectual disabilities and autism. However, technology use in education often mimics traditional methods rather than innovating.

The literature survey introduces “smart education,” which leverages assistive technologies and personalized learning plans to adapt education to each student’s needs, including those with disabilities. Technologies such as adaptive learning platforms and mobile learning tools offer promising personalized and accessible educational experiences, though challenges remain in fully addressing diverse learning styles and accessibility requirements.

The methodology describes a qualitative study investigating special education teachers’ attitudes toward and use of technology. Teachers generally have access to modern devices (computers, tablets, smart boards) and use technology for monitoring student performance and providing feedback. However, financial constraints and lack of specialized materials for special education are major challenges. Teachers see potential in technologies for teaching cognitive, psychomotor, and emotional skills, including self-care and socialization, citing examples like Kinect technology.

The results highlight that sign language interpreters significantly improve communication access for Deaf and Hard-of-Hearing students, increasing understanding and participation by around 90%, with interpretation accuracy at 95%, underscoring the need for trained interpreters.

Conclusion

The objective of this study was to recognize the views of special education teachers towards educational technologies and their views regarding educational technologies that would be created by the project that aimed to create instructional materials for special education teachers and students. As the initial step in the project, through qualitative research methodology, a needs analysis was done to examine the current and desired state of technology application in special education classrooms. Data gathered from special education teachers were analyzed through content analysis technique. Following analysis, four overarching themes emerged from the data. First, participants provided comments on their use of technology in their classrooms. Teachers mostly employ technology for maintaining student records and accessing instructional materials or information on special education. They employ animations in computer or video format as well. Nevertheless, as a result of inadequate infrastructure, study material, and family lack of access to technology, technology is not being employed as appropriately in special education classes. One of the better-documented obstacles to technology integration is lack ofaccess to the technological infrastructure and technology itself (Bingaman, 2009; Pittman & Gaines, 2015; Ertmer, 1999; Hew & Brush, 2006).

References

[1] Lewis, S., & Clarke, M. (2015). Assistive Technology and People with Disabilities. Springer. [2] Bashar, M., Rashid, M. M., & Jovanovic, J. (2019). Personalized Learning Plan (PLP) Framework. IEEE Access, 7,123456–123467. [3] Vanderheiden, G., Treviranus, J., & Iser, H. (2018). Inclusive Design for a Digital World: Designing with Accessibility in Mind. O\'Reilly Media. [4] Crompton, H. (2013). A Historical Overview of Mobile Learning: Toward Learner-Centered Education. In Z. L. Berge & L. Y. Muilenburg (Eds.), Handbook of Mobile Learning (pp. 3–14). Routledge. [5] Alghamdi, A. S., Alzahrani, A. A., & Alzahrani, A. A. (2022). Real-Time Sign Language Translation Systems: A Review Study. MDPI Computers, 11(5),78. [6] Novopoltsev, M., Sinitca, A., Likhachov, P., & Kotov, I. (2023). Fine-Tuning of Sign Language Recognition Models. arXiv Preprint, arXiv:2302.07693. [7] Moryossef, A., Wolf, L., & Goldberg, Y. (2020). Real-Time Sign Language Detection Using Human Pose Estimation. arXiv Preprint, arXiv:2008.04637. [8] Kumar, R., Bajpai, A., & Sinha, A. (2023). Mediapipe and CNNs for Real-Time ASL Gesture Recognition. arXiv Preprint, arXiv:2305.05296. [9] Ma, J., Gao, W., & Wang, C. (2024). Stream State-Tying for Sign Language Recognition. arXiv Preprint, arXiv:2407.10975. [10] Novopoltsev, M., Sinitca, A., Likhachov, P., & Kotov, I. (2023). Fine-Tuning of Sign Language Recognition Models. arXiv Preprint, arXiv:2302.07693.

Copyright

Copyright © 2025 Aditi Rane, Shrutika Gurav, Aditya Singh, Anvita Birje. This 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.