Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM65536
Volume:
10 |
6 |
Jun 2026
Pages:
1-9
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 Computer Science and Engineering
Avinashilingam Institute for Home Science and Higher Education for Women
Department of Computer Science and Engineering
Avinashilingam Institute for Home Science and Higher Education for Women
Department of Computer Science and Engineering
Avinashilingam Institute for Home Science and Higher Education for Women
Department of Computer Science and Engineering
Avinashilingam Institute for Home Science and Higher Education for Women
Assistant Professor , Department of Computer Science and Engineering
Avinashilingam Institute for Home Science and Higher Education for Women
Communication remains a significant challenge for individuals with visual, hearing, speech, and multiple impairments, particularly when interacting with people who have different accessibility needs. This paper presents UNITALK – Connect Everyone, an AI-powered communication application designed to support inclusive interaction through automatic ability detection and adaptive user interfaces. The system classifies users based on simple tap-assisted assessments and dynamically customizes communication modes for Normal, Blind, Deaf, Speech-Impaired, Deaf-Dumb, and Blind-Dumb users. By integrating Speech-to-Text (STT), Text-to-Speech (TTS), real-time messaging, and profile-based interface adaptation, the application enables effective communication across different disability groups. The solution is implemented using React Native (Expo), FastAPI, Socket.io, and MongoDB, providing a scalable and user-friendly platform without requiring specialized hardware or complex setup. Experimental evaluation demonstrated reliable profile detection, effective message conversion, and smooth real-time interaction. The proposed system contributes to accessible technology by offering a unified platform that promotes inclusion, independence, and equal access to digital communication.
KEYWORDS
This paper presented UNITALK – Connect Everyone, an AI-powered accessible communication application that bridges communication barriers between users with diverse disabilities and normal users. By automating user ability detection and dynamically adapting the interface and message format to each user's profile, UNITALK delivers a unified, inclusive platform that removes the need for separate, disability-specific tools. The system integrates Speech-to-Text, Text-to-Speech, real-time adaptive messaging, and persistent user profiles through a modern technology stack comprising React Native, FastAPI, Socket.io, and MongoDB. Tested across multiple user profiles, the platform demonstrated accurate ability detection, reliable voice conversion, and seamless cross-disability communication without requiring any manual setup or specialised hardware. Future work will focus on: integrating advanced AI models for personalised communication assistance based on user behaviour; real-time multilingual support; a production-grade mobile application for broader distribution; advanced gesture recognition and 3D sign language avatar rendering; and scalable cloud integration with enhanced security. These enhancements will further extend UNITALK's reach and effectiveness for differently-abled communities worldwide
[1] Y. Zhang, "A Study on the Translation of Spoken English from Speech to Text," IEEE Journal of ICT Standardization, 2023. [2] B. A. Abdullah, G. A. Amoudi, and H. S. Alghamdi, "Advancements in Sign Language Recognition: A Comprehensive Review and Future Prospects," IEEE Access, 2023. [3] M. Balachandra and A. Manjula, "Multimodal Real-Time Translation System for Hearing Impaired Accessibility Using Deep Learning," IEEE Access, 2023. [4] "Speech Processing Research Article," Journal of Natural Language Processing (J-STAGE), DOI: https://doi.org/10.5715/jnlp.31.935, 2024. [5] "Systematic Approach for Speech to Text Translation and Summarization," Indian Journal of Science and Technology, DOI: 10.17485/IJST/v18i28.470, 2025. [6] "Introduction to Web Accessibility," W3C Web Accessibility Initiative (WAI). Available: https://www.w3.org/WAI/fundamentals/accessib ility-intro/ [7] "Web Speech API," MDN Web Docs. Available: https://developer.mozilla.org/en-US/docs/Web/API/Web_Speech_API
Publication Date
6/26/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
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...