Multimodal Emotion Recognition Using a Spontaneous Filipino Emotion Database

Author

Dy, Marc Lanze Ivan C ; Espinosa, Ivan Vener L ; Go, Paul Patrick V ; Mendez, Charles Martin M ; Cu, Jocelynn W.

Author_Institution

Center for Empathic Human-Comput. Interactions, De La Salle Univ., Manila, Philippines

fYear

2010

fDate

11-13 Aug. 2010

Firstpage

1

Lastpage

5

Abstract

Human-computer interaction is moving towards giving computers the ability to adapt and give feedback in accordance to a user´s emotion. Studies on emotion recognition show that combining face and voice signals produce higher recognition rates compared to using either one individually. In addition, majority of the emotion corpus used on these systems were modeled based on acted data with actors who tend to exaggerate emotions. This study focus on the development of a multimodal emotion recognition system that is trained using a spontaneous Filipino emotion database. The system extracts voice features and facial features that are then classified into the correct emotion label using support vector machines. Based on test results, recognizing emotions using voice only yielded 40% accuracy; using face only, 86%; and using a combination of voice and face yielded 80%.

Keywords

emotion recognition; face recognition; feature extraction; human computer interaction; support vector machines; facial feature extraction; human computer interaction; multimodal emotion recognition; spontaneous Filipino emotion database; support vector machine; voice feature extraction; Accuracy; Emotion recognition; Face; Face recognition; Feature extraction; Speech recognition; Support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Human-Centric Computing (HumanCom), 2010 3rd International Conference on

Conference_Location

Cebu

Print_ISBN

978-1-4244-7567-4

Type

conf

DOI

10.1109/HUMANCOM.2010.5563314

Filename

5563314