Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM62865
Volume:
10 |
5 |
May 2026
Pages:
1-6
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Department of Information technology
Sinhgad College Of Engineering, Vadgaon bk Pune
Department of Information technology
Sinhgad College Of Engineering, Vadgaon bk Pune
Department of Information technology
Sinhgad College Of Engineering, Vadgaon bk Pune
Department of Information technology
Sinhgad College Of Engineering, Vadgaon bk Pune
Department of Information technology
Sinhgad College Of Engineering, Vadgaon bk Pune
Department of Information technology
Sinhgad College Of Engineering, Vadgaon bk Pune
Department of Information technology
Sinhgad College Of Engineering, Vadgaon bk Pune
Department of Information technology
Sinhgad College Of Engineering, Vadgaon bk Pune
Department of Information technology
Sinhgad College Of Engineering, Vadgaon bk Pune
Department of Information technology
Sinhgad College Of Engineering, Vadgaon bk Pune
Communication barriers between deaf, mute, and hearing individuals continue to limit social inclusion and accessibility in everyday interactions. While existing solutions provide partial support, many are either hardware-dependent, costly, or lack real-time bidirectional capabilities. This paper presents SignBridgeAI , an AI-powered, lightweight, and browser-based multimodal communication system designed to enable seamless interaction using Indian Sign Language (ISL). The system integrates real-time sign-to-text recognition, text-to-speech conversion, and text-to-sign (ISL fingerspelling) using web technologies. Unlike traditional approaches, it operates entirely within a web environment without requiring specialized hardware. The proposed system uses MediaPipe for hand tracking, a trained deep learning model for gesture classification, and browser-based APIs for speech synthesis.Additionally, deployment on the Internet Computer enables decentralized, serverless, and always-available access. Experimental evaluation demonstrates efficient real-time performance with high usability and low latency, making the system suitable for practical communication scenarios. The proposed solution contributes toward scalable, affordable, and inclusive assistive technology.
KEYWORDS
This paper presented SignBridge AI, an innovative AI- powered multimodal platform that bridges communication gaps among deaf, mute, blind, and hearing individuals via real-time sign language recognition, speech-to-text conversion, and animated avatar translations. The system achieves high accuracy, low latency, and broad accessibility using standard consumer devices. Pilot testing indicates improved communication efficacy and user acceptance. Future work will focus on expanding the sign language vocabulary to include regional and contextual variations, incorporating advanced natural language processing for nuanced interpretation. Enhancements in avatar realism and emotion expression will be pursued to enrich interactions. Additionally, integrating tactile or haptic feedback could broaden accessibility for deaf-blind users. Further scalability improvements aim to support larger user bases and offline capabilities. Overall, SignBridge AI is poised to make a substantial societal impact by enabling inclusive and effective communication for differently- abled communities.
[1]. M. Faisal, M. Alsulaiman, M. Mekhtiche, M. Bencherif, M. Algabri, T. Alrayes, G. Muhammad, H. Mathkour, W. Abdul, Y. Alohali, M. Al-Hammadi, H. Altaheri, and T. Alfakih, "Enabling two-way communication of deaf using Saudi sign language," IEEE Access, vol. 12, pp. 1–18, 2023, doi: 10.1109/ACCESS.2023.3337514. [2]. I. Marin, V. Babalain, and S. Slutu, "Real-Time Sign Language-to-Speech Translation System With AI- Powered Wearable Technology," IEEE Access, vol. 13,pp. 151652–151663,Sept.2025,doi: 10.1109/ACCESS.2025.3602794. [3]. A. M. Ravishankkar, B. Balavishwa, S. Chandru, M.S. Dharinendra, and M. Sanjay, "AI-powered Signtone deaf companion system for inclusive communication between deaf and hearing individuals," Journal of Emerging Trends and Novel Research, vol. 3, no. 4, Apr. 2025, pp. a153–a160. [4]. A. M. Anitha, P. Annanya, R. C. Venkata Shritha, K. Hargun, and M. H. S. Mangala, "Sign Language Conversion to Text and Speech Using Machine Learning," International Journal of Innovative Research in Technology, vol. 10, no. 12, pp. 2846-2851, May 2024. [5]. H. Kim, I. Lee, S. Panda, S. Hajra, B. Jeong, J. Seo, K. R. Kaja, M. A. Belal, V. Vivekananthan, and H. J. Kim, "Smart gloves-based triboelectric nanogenerator for sign language detection," Micro and Nano Systems Letters, vol. 13, no. 11, 2025, doi: 10.1186/s40486-025-00231-7.
Publication Date
5/8/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
1
Total views since publication
PDF Downloads
5
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...