next up previous
Next: Introduction

444Appears in: Proceedings of the ICASSP '98

Digital Processing of Affective Signals

Jennifer Healey and Rosalind Picard
Rm E15-389, The Media Laboratory
Massachusetts Institute of Technology
20 Ames St., Cambridge, MA 02139
fenn@media.mit.edu, picard@media.mit.edu

Abstract:

Affective signal processing algorithms were developed to allow a digital computer to recognize the affective state of a user who is intentionally expressing that state. This paper describes the method used for collecting the training data, the feature extraction algorithms used and the results of pattern recognition using a Fisher linear discriminant and the leave one out test method. Four physiological signals, skin conductivity, blood volume pressure, respiration and an electromyogram (EMG) on the masseter muscle were analyzed. It was found that anger was well differentiated from peaceful emotions (90%-100%), that high and low arousal states were distinguished (80%-88%), but positive and negative valence states were difficult to distinguish (50%-82%). Subsets of three emotion states could be well separated (75%-87%) and characteristic patterns for single emotions were found.



 

Jennifer Healey - fenn@media.mit.edu
1999-02-11