Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.14 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
Efficient telephonic communication remains a critical operational requirement in both educational institutions and healthcare systems, where high volumes of routine interactions such as appointment scheduling, enquiry handling, and follow-up notifications are common. Traditional communication methods, including manual calling and rule-based Interactive Voice Response (IVR) systems, often suffer from inefficiency, rigidity, and lack of contextual understanding. This paper presents a low-latency multilingual AI voice agent designed to enable real time, human-like telephonic interactions. The proposed system integrates Automatic Speech Recognition (ASR), Large Language Model (LLM)- driven dialogue management, and Text-to-Speech (TTS) within a unified pipeline optimized for minimal response delay. A key contribution is the incorporation of an uncertainty-aware dialogue orchestrator, which improves reliability by dynamically handling ambiguous inputs through clarification or escalation mechanisms. Additionally, the system supports multilingual communication with code-switching capabilities, making it suitable for linguistically diverse environments. A goal-oriented conversational framework ensures efficient task completion, while secure telephony integration enables seamless deployment in real-world scenarios. Experimental evaluation demonstrates reduced latency (~500 ms), high task completion rates (>90%), and improved user satisfaction, highlighting the system’s effectiveness in automating telephonic workflows in sensitive domains.
"Multilingual Low-Latency AI Voice Agent for Automated Telephonic Interactions in Education and Healthcare", International Journal for Research Trends and Innovation (www.ijrti.org), ISSN:2456-3315, Vol.11, Issue 4, page no.c34-c37, April-2026, Available :http://www.ijrti.org/papers/IJRTI2604278.pdf
Downloads:
000205506
ISSN:
2456-3315 | IMPACT FACTOR: 8.14 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.14 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator