AIMS TALK: Intelligent Call Center Support in Bangla Language with Speaker Authentication

Shehan Irteza Pranto, Rahad Arman Nabid, Ahnaf Mozib Samin, Nabeel Mohammed, Farhana Sarker, Mohammad Nurul Huda, Khondaker A. Mamun

Dec 2021

Abstract

Call support centers operate over the telephone, connect between customers and receptionists to ensure customer satisfaction by solving their problems. Due to pandemics, customer call support centers have become a popular way of communication that has been used in different domains such as e-commerce, hospitals, banks, credit card support, government offices. Moreover, humans’ limitations to serve 24 hours a day and the fluctuation of waiting time makes it more challenging to satisfy all the customers over call center. So, customer service needs to be automated to handle customers by providing a domain-based response in the native language, especially in a developing country like Bangladesh, where call support centers are increasing. Although most people use the Bangla language to communicate, little work has been done in customer care automation in the native language. Our developed architecture, “AIMS TALK” can respond to that customer’s need by recognizing users’ voices, specifying customers’ problems in the standardized Bangla language, collecting customers’ responses to the database to give feedback according to the queries. Besides, the system uses MFCC feature extraction for speaker recognition with an average accuracy of 94.38% on 42 people in real-time testing, an RNN-based model for Bangla Automatic Speech Recognition (ASR) with a word error rate (WER) of 42.15%, and sentence summarization we used Sentence similarity measurement technique having an average loss of 0.004. Lastly, we used gTTS that works as Text to Speech Synthesis for the Bangla language in WavNet architecture.

Type Conference paper

Publication ETCCE, Bangladesh

Publisher IEEE