Classification of emotional speech units in call centre interactions

Author

Galanis, Dimitrios ; Karabetsos, Sotiris ; Koutsombogera, Maria ; Papageorgiou, Harris ; Esposito, Anna ; Riviello, Maria-Teresa

Author_Institution

Inst. for Language & Speech Process.- Athena R.C., Athens, Greece

fYear

2013

fDate

2-5 Dec. 2013

Firstpage

403

Lastpage

406

Abstract

Detecting emotional traits in call centre interactions can be beneficial to the quality management of the services provided, since this reveals the positioning of both speakers, i.e. satisfaction or frustration and anger on the customers´ side, and stress detection, disappointment mitigation or failure to provide the requested service on the operators´ side. This paper describes a machine learning approach to classify emotional speech units occurring in a call centre dataset by employing emotion-related labels, automatically extracted acoustic features as well as additional context-related features.

Keywords

call centres; emotion recognition; feature extraction; learning (artificial intelligence); pattern classification; quality management; speech processing; acoustic feature extraction; call centre dataset; call centre interactions; context related features; disappointment mitigation; emotion related labels; emotional speech unit classification; emotional traits detection; machine learning; quality management; stress detection; Accuracy; Acoustics; Feature extraction; Speech; Speech processing; Speech recognition; Training; SVM; call centre interactions; emotion classification; emotional speech;

fLanguage

English

Publisher

ieee

Conference_Titel

Cognitive Infocommunications (CogInfoCom), 2013 IEEE 4th International Conference on

Conference_Location

Budapest

Print_ISBN

978-1-4799-1543-9

Type

conf

DOI

10.1109/CogInfoCom.2013.6719279

Filename

6719279