Binary classification performances of emotion classes for Turkish Emotional Speech

Author

Oflazoglu, Caglar ; Yildirim, Serdar

Author_Institution

Bilgisayar Muhendisligi Bolumu, Mustafa Kemal Univ., Hatay, Turkey

fYear

2015

fDate

16-19 May 2015

Firstpage

2353

Lastpage

2356

Abstract

Emotion recognition from speech plays important role for natural human-computer interaction. This study investigates binary classification performances of 4 fundamental emotion classes in Turkish Emotional Speech (TurES) Database using acoustic features for various classifiers. Results shows that Angry emotion class has higher classification rate (70%-80%) than others; lowest classification rate is obtained as 64% for Happy-Neutral emotion pair. Best classification results are obtained with J48 (C4.5) classifier for all emotion pairs.

Keywords

acoustic signal processing; emotion recognition; human computer interaction; signal classification; speech recognition; J48-C4.5 classifier; TurES Database; Turkish emotional speech database; acoustic features; angry emotion class; binary classification performances; classification rate; emotion recognition; happy-neutral emotion pair; natural human-computer interaction; Acoustics; Databases; Emotion recognition; Manganese; Speech; Speech recognition; Support vector machines; TurES database; binary classification; categorical classification; emotional speech; pattern recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing and Communications Applications Conference (SIU), 2015 23th

Conference_Location

Malatya

Type

conf

DOI

10.1109/SIU.2015.7130352

Filename

7130352