Abstract | ||
---|---|---|
The design of intelligent personalized interactive systems, having knowledge about the user's state, his desires, needs and wishes, currently poses a great challenge to computer scientists. In this study we propose an information fusion approach combining acoustic, and biophysiological data, comprising multiple sensors, to classify emotional states. For this purpose a multimodal corpus has been created, where subjects undergo a controlled emotion eliciting experiment, passing several octants of the valence arousal dominance space. The temporal and decision level fusion of the multiple modalities outperforms the single modality classifiers and shows promising results. |
Year | Venue | Keywords |
---|---|---|
2011 | HCI (3) | biophysiological data,great challenge,emotional state,Multimodal emotion classification,multiple modality,decision level fusion,naturalistic user behavior,intelligent personalized interactive system,computer scientist,information fusion approach,multiple sensor,controlled emotion |
Field | DocType | Volume |
Confusion matrix,Decision level,Multiple modalities,Computer science,Emotion recognition,Emotion classification,Human–computer interaction,Valence arousal,Information fusion,Multiple sensors | Conference | 6763 |
ISSN | Citations | PageRank |
0302-9743 | 25 | 1.18 |
References | Authors | |
6 | 10 |
Name | Order | Citations | PageRank |
---|---|---|---|
Steffen Walter | 1 | 127 | 13.34 |
Stefan Scherer | 2 | 1159 | 73.43 |
Martin Schels | 3 | 277 | 15.88 |
Michael Glodek | 4 | 295 | 16.76 |
David Hrabal | 5 | 73 | 6.01 |
Miriam Schmidt | 6 | 128 | 6.23 |
Ronald Böck | 7 | 99 | 10.75 |
Kerstin Limbrecht | 8 | 27 | 1.56 |
Harald C. Traue | 9 | 129 | 13.48 |
Friedhelm Schwenker | 10 | 1160 | 96.59 |