Skip to content
Conference

AI Based FAQ Chatbot with Voice Assistance of GRIET

Aug 2026 · International Conference Computational Vision and Bio Inspired Computing · pp. 849-855 · 0 citations · 16 references

Abstract

This proposed system centers around the creation of an AI-based FAQ Chatbot with Voice Assist. This Chatbot allows users to interact with the service using natural voice commands. In the conventional approach, the FAQ section is handled by the support staff, but this system automates the entire process using Artificial Intelligence. Using a browser, the chatbot collects the user's voice data, transcribes the audio using speech recognition, and applies NLP techniques like TF-IDF and cosine similarity to retrieve the most relevant answer from the stored FAQ data. If there is a lack of confidence in answering the question, the input is stored as an unknown answer for administration review and the user input is captured as unanswered questions. These questions can then be reviewed by admins and appropriate responses provided which will allow the admin to refine the stored responses, thus enhancing the system's intelligence. Furthermore, the responses are delivered through text-to-speech outputs which allow users to listen to the answers. By integrating voice commands, responsive intelligent interface, and the admin feedback loop, the system's capability to enhance user experiences and refine self-responding systems through continuous improvement is extraordinary. The proposed system was tested with 496 test queries, comprising of original and rephrased FAQ queries, and the accuracy of response was found to be 97.58% with an average retrieval time of 0.0018 seconds.

View source

Similar papers

Open access Sep 2026

SpeakOne: Multilingual AI Chatbot for Student Support

Higher education organizations face a huge number of repetitive inquiries from students regarding admissions, fee payments, exams, scholarships, placements, and other campus-related aspects. Inquiries are made in various languages, resulting in communication difficulties and increased work pressure on the administrativ...

Abhijit Shankar Jadhav, Gajul N. B. · 0 citations
Review 2026

AI-Based Chatbots: A Comprehensive Study of Architecture, Applications, Performance, Challenges, Ethics, and Future Perspectives

Artificial intelligence (AI) chatbots powered by natural language processing (NLP) have transformed human-computer interaction across sectors such as e-commerce, healthcare, and customer service. This paper reviews the evolution of chatbot technology, with a particular focus on the components that constitute modern sys...

S. Nalawade, H. Tapase, Shreya Jadhav · 0 citations
Open access Sep 2026

A Retrieval-Augmented Multilingual Chatbot for Intelligent College Information Services

The experimental results obtained were 92% response accuracy, 90% retrieval relevance, 1.8 s response time on average, and 91% user satisfaction, thus proving the efficiency of the suggested architecture in providing reliable and scalable academic information services.

Arun Babu P., P. Sree, Lingala Anusha et al. · 0 citations
#generative ai Open access Sep 2026

AI Powered College Enquiry Chatbot

This project presents an AI-Powered College Enquiry Chatbot that automates common college-related queries using Retrieval-Augmented Generation (RAG) and provides an administrative dashboard for managing FAQ content and monitoring chatbot performance.

G. Vamsi, N. Charan · 0 citations
Open access Aug 2026

Context-Aware Large Language Model for Customer Support Chatbots

The results show that the RAG architecture provides a scalable alternative for creating precise, contextually grounded conversational agents, thereby mitigating some of the main drawbacks of LLMs.

Rabia Shabbir, K. Talpur, Shakeel Ahmad · 0 citations
Preprint Sep 2026

RePlay: Retrieval-Based Voice Playback for Multi-Turn spoken dialogue

Many voice interaction applications require exact control over both the content and delivery of responses, typically using pre-recorded lines. Recent full-duplex models respond with low latency but cannot guarantee exact content or reproduce a specific recorded performance, while cascaded systems can be constrained to...

Sathvik Udupa, Naveen Kumar, Ryan Folmsbee · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.