| Issue |
EPJ Web Conf.
Volume 367, 2026
Fifth International Conference on Robotics, Intelligent Automation and Control Technologies (RIACT 2026)
|
|
|---|---|---|
| Article Number | 04006 | |
| Number of page(s) | 8 | |
| Section | AI & Machine Learning | |
| DOI | https://doi.org/10.1051/epjconf/202636704006 | |
| Published online | 29 April 2026 | |
https://doi.org/10.1051/epjconf/202636704006
Multilingual AI voice assistant for campus navigation and announcements
1 Department of Computer Science and Engineering (AIML), KPR Institute of Engineering and Technology, Coimbatore, India
2 Department of Computer Science and Engineering, KPR Institute of Engineering and Technology, Coimbatore, India
3 Department of Electrical and Electronics Engineering, KPR Institute of Engineering and Technology, Coimbatore, India
* Corresponding Author: This email address is being protected from spambots. You need JavaScript enabled to view it.
Published online: 29 April 2026
Abstract
Comprehensive navigation and information access remain significant issues in vast educational campuses with linguistic diversities. This re- search proposes an innovative conversational AI system that integrates automatic speech recognition in three languages, semantic interpretation, retrieval- augmented knowledge synthesis, graph optimization, and gesture recognition to provide unified information access and navigation services in the educational campuses. The proposed system has been evaluated through systematic evaluation with 2,500 authentic user interactions via mobile apps, web portals, and kiosks. The quantitative results show that the proposed system has achieved 92.3% accuracy in intent classification, 89.2% accuracy in route finding, and sub-2-second response time with complete fidelity to the data sources under various environmental conditions, proving its superiority over traditional web portal-based information access systems.
© The Authors, published by EDP Sciences, 2026
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.