Prediction of emotional states in parent-adolescent conversations using non-linear autoregressive neural networks

Stolar, MN; Lech, M; Burnett, IS

Prediction of emotional states in parent-adolescent conversations using non-linear autoregressive neural networks

Stolar, MN Lech, M Burnett, IS

Permalink

Publication Type:: Conference Proceeding
Citation:: 2015, 9th International Conference on Signal Processing and Communication Systems, ICSPCS 2015 - Proceedings, 2015
Issue Date:: 2015-01-01

Closed Access

	Filename	Description	Size
	07391785.pdf	Published version	773.12 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Stolar, MN	en_US
dc.contributor.author	Lech, M	en_US
dc.contributor.author	Burnett, IS https://orcid.org/0000-0003-3795-7722	en_US
dc.date.issued	2015-01-01	en_US
dc.identifier.citation	2015, 9th International Conference on Signal Processing and Communication Systems, ICSPCS 2015 - Proceedings, 2015	en_US
dc.identifier.isbn	9781467381185	en_US
dc.identifier.uri	http://hdl.handle.net/10453/92702
dc.description.abstract	© 2015 IEEE. This study investigates an application of nonlinear autoregressive (NAR) models to the prediction of the most likely time series of emotional state transitions of speakers engaged in dyadic conversations. While, previous methods analyzed each speaker in separation, the new approach proposes to couple both speakers into a nonlinear recursive predictive neural network system (NARX-NN). The NARX-NN system was tested and compared with its uncoupled version (NAR-NN). The tests were conducted using speech recordings from 63 parent-child dyads including 29 depressed and 34 non-depressed adolescent children, 14-18 years of age. The conversations were conducted on three different topics. The NARX-NN outperformed the NAR-NN method in all experimental scenarios and across all topics of conversation. Predictions of emotional states for depressed children led to higher accuracy than the predictions for non-depressed children. Modeling with class and/or speaker dependency improved the results compared to the class and/or speaker independent models.	en_US
dc.relation.ispartof	2015, 9th International Conference on Signal Processing and Communication Systems, ICSPCS 2015 - Proceedings	en_US
dc.relation.isbasedon	10.1109/ICSPCS.2015.7391785	en_US
dc.title	Prediction of emotional states in parent-adolescent conversations using non-linear autoregressive neural networks	en_US
dc.type	Conference Proceeding
utslib.for	0906 Electrical and Electronic Engineering	en_US
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
utslib.copyright.status	closed_access
pubs.publication-status	Published	en_US

Abstract:

© 2015 IEEE. This study investigates an application of nonlinear autoregressive (NAR) models to the prediction of the most likely time series of emotional state transitions of speakers engaged in dyadic conversations. While, previous methods analyzed each speaker in separation, the new approach proposes to couple both speakers into a nonlinear recursive predictive neural network system (NARX-NN). The NARX-NN system was tested and compared with its uncoupled version (NAR-NN). The tests were conducted using speech recordings from 63 parent-child dyads including 29 depressed and 34 non-depressed adolescent children, 14-18 years of age. The conversations were conducted on three different topics. The NARX-NN outperformed the NAR-NN method in all experimental scenarios and across all topics of conversation. Predictions of emotional states for depressed children led to higher accuracy than the predictions for non-depressed children. Modeling with class and/or speaker dependency improved the results compared to the class and/or speaker independent models.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/92702