Conversational Interactive Voice Response System with few-shot intent classifier

Abhinav Parag Mishra; Rishabh Shukla; Manish Pandey; Gyanendra Nath Dwivedi

Conversational Interactive Voice Response System with few-shot intent classifier

Authors: Abhinav Parag Mishra, Rishabh Shukla, Manish Pandey, Gyanendra Nath Dwivedi

Unique Paper ID: 151741
Volume: 8
Issue: 1
PageNo: 719-722

Keywords: Dual sentence encoder Intent classifier Interactive Voice Response (IVR) VoiceXML

Abstract:
Interactive Voice Response (IVR) systems have been helping businesses in providing support to their customers over a telephone network. Modern IVRs not only have speech recognition facility, but also have an AI-powered conversational system with intent classifier. Such IVRs improve user experience, but building such a system is resource-intensive and labor-intensive process. Resources are required to fine-tune and train the intent classifier every time an intent is added. The labor-intensive part of the process is creating a domain specific labelled dataset for training the intent classifier. In this paper, we propose a smart IVR system with intent classifier based on dual sentence encoders. The intent classifier used not only requires very less resources for training, but also works better than models like fine-tuned BERT in few-shot setups (when examples per intent are less). Cost of building conversational IVR is brought down even more when such intent classifier is built in conjunction with open-source technologies like Asterik (for voice server) and Festival (for text-to-speech conversion).

Download article

email to a friend

Cite This Article

ISSN: 2349-6002
Volume: 8
Issue: 1
PageNo: 719-722

Conversational Interactive Voice Response System with few-shot intent classifier

Available:https://ijirt.org/Article?manuscript=151741

Impact Factor
8.01 (Year 2024)

UGC Approved
Journal no 47859

Join Our IPN

IJIRT Partner Network

Submit your research paper and those of your network (friends, colleagues, or peers) through your IPN account, and receive 800 INR for each paper that gets published.

Join Now