Call Transcription Methodology for Contact Center Systems

Miroslaw Plaza,Stanislaw Deniziak,Lukasz Pawlik

doi:10.1109/access.2021.3102502

Miroslaw Plaza, Stanislaw Deniziak + Show 1 more

Open Access

https://doi.org/10.1109/access.2021.3102502

Copy DOI

Journal: IEEE Access	Publication Date: Jan 1, 2021
Citations: 8	License type: CC BY 4.0

Abstract

Nowadays, one of the key areas of research on contact centre systems is their automation. The main element that influences the possibility of automation of contact centre processes is the call transcription methods implemented by automatic speech recognition (ASR) systems. Such systems enable developing intention recognition methods and, consequently voice bots. The current solutions used in ASR systems for many less popular languages do not guarantee a fully satisfactory transcription quality for hotline voice calls. This is due to the unique characteristics of the sound signal generated there, whose quality parameters differ significantly from those of studio recordings. The paper presents a comparative study of selected speech recognition systems that were additionally supplemented with elements of preprocessing of sound recordings and postprocessing of originally produced transcriptions. As for preprocessing, the following methods were tested: separation of the client and agent channels into two independent signals, training of ASR systems, and audio signal correction. With regards to postprocessing, on the other hand, tests were performed for inarticulate sounds, normalization of standard phrases (e.g. numbers, dates, times, etc.), and identification of close-sounding phrases and foreign language phrases, and lemmatization. Based on the research conducted and the analyses performed, a new method of call transcription intended specifically for contact center systems was proposed. The research conducted for this paper was based on the Polish language model, for which major problems are observed with the quality of automatic contact center call transcriptions.

Highlights

The development of call/contact centre (CC) systems observed in recent years is largely focused on the automation of many of processes performed there
In the initial phase of the work, a first database of sound recordings was created, which included 754 real conversations between a customer and an agent on a CC hotline. These samples were used during work on the development and optimization of a transcription method for CC systems supporting the Polish language
This study formed the basis for the development of a new transcription method, presented in section IV, intended for CC systems that support the Polish language

Summary

Introduction

The development of call/contact centre (CC) systems observed in recent years is largely focused on the automation of many of processes performed there. Automation of routine tasks, on the one hand, makes it possible to reduce costs generated by CC systems and, on the other hand, is important for social reasons, as it relieves agents from the need to perform tedious, repetitive tasks. This greatly improves the comfort of agents’ work, preventing turnover in this difficult job [1]. There are many different ASR systems on the market today, both free and offered on a commercial basis These systems are characterized by many different parameters that determine the possibility of their use in the development of intention recognition methods.

Objectives

Methods

Results

Conclusion