A multimodal emotion corpus for Filipino and its uses
College
College of Computer Studies
Department/Unit
Computer Technology
Document Type
Article
Source Title
Journal on Multimodal User Interfaces
Volume
7
Issue
1-2
First Page
135
Last Page
142
Publication Date
1-1-2013
Abstract
This paper describes the Filipino multimodal emotion database (FilMED). FilMED was built with the purpose of developing affective systems for TALA, which is an ambient intelligent empathic space. We collected a total of 11,430 audio-video clips showing acted and spontaneous expressions of emotion involving 25 subjects. We used Filipino emotion labels to annotate the emotion, which includes: kasiyahan (happiness), kalungkutan (sadness), galit (anger), takot (fear), gulat (surprise), and pandidiri (disgust). We also engaged 20 coders to annotate the clips with valence and arousal values using Feeltrace. To show the usefulness of the database, we presented three automatic affect recognition systems that used FilMED to build the affect models.
html
Digitial Object Identifier (DOI)
10.1007/s12193-012-0114-8
Recommended Citation
Cu, J. W., Solomon, K. C., Suarez, M. C., & Sta. Maria, M. A. (2013). A multimodal emotion corpus for Filipino and its uses. Journal on Multimodal User Interfaces, 7 (1-2), 135-142. https://doi.org/10.1007/s12193-012-0114-8
Disciplines
Computer Sciences
Keywords
Emotion recognition—Data processing
Upload File
wf_yes