A multi-modal automatic monitoring system oriented speech service quality of call center

Abstract

Call center system has become an integral part of business operations, monitoring speech service quality is a vital work of the management in call center. Currently main scoring approach is manual control mode. It's efficiency is not high and it is difficult to uniform standard. This paper presents an automatic multi-mode monitoring system for speech service quality of call center, and keyword spotting technology is applied to monitor the speech content automatically. In order to make up the defects of single-mode keyword spotting, this paper uses speech emotion recognition technology to identify the mood of the speech. Finally, system monitors parallel with multi-modal and scoring results. This will not only meet to monitor the content of the speech but also realize to recognize the emotion. © 2013 Springer Science+Business Media.