Research Article
Assessing Bipolar Episodes Using Speech Cues Derived from Phone Calls
439 downloads
@INPROCEEDINGS{10.1007/978-3-319-11564-1_11, author={Amir Muaremi and Franz Gravenhorst and Agnes Gr\'{y}nerbl and Bert Arnrich and Gerhard Tr\o{}ster}, title={Assessing Bipolar Episodes Using Speech Cues Derived from Phone Calls}, proceedings={Pervasive Computing Paradigms for Mental Health. 4th International Symposium, MindCare 2014, Tokyo, Japan, May 8-9, 2014, Revised Selected Papers}, proceedings_a={MINDCARE}, year={2014}, month={12}, keywords={Bipolar disorder Smartphone Voice analysis Phone calls}, doi={10.1007/978-3-319-11564-1_11} }- Amir Muaremi
Franz Gravenhorst
Agnes Grünerbl
Bert Arnrich
Gerhard Tröster
Year: 2014
Assessing Bipolar Episodes Using Speech Cues Derived from Phone Calls
MINDCARE
Springer
DOI: 10.1007/978-3-319-11564-1_11
Abstract
In this work we show how phone call conversations can be used to objectively predict manic and depressive episodes of people suffering from bipolar disorder. In particular, we use phone call statistics, speaking parameters derived from phone conversations and emotional acoustic features to build and test user-specific classification models. Using the random forest classification method, we were able to predict the bipolar states with an average F1 score of 82 %. The most important variables for prediction were speaking length and phone call length, the HNR value, the number of short turns and the variance of pitch F.
Copyright © 2014–2024 ICST
