Towards an artificial therapy assistant: Measuring excessive stress from speech

Frans van der Sluis; Egon van den Broek; Ton Dijkstra

Towards an artificial therapy assistant: Measuring excessive stress from speech

Frans van der Sluis, Egon van den Broek, Ton Dijkstra

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

2 Citations (Scopus)

176 Downloads (Pure)

Abstract

The measurement of (excessive) stress is still a challenging endeavor. Most tools rely on either introspection or expert opinion and are, therefore, often less reliable or a burden on the patient. An objective method could relieve these problems and, consequently, assist diagnostics. Speech was considered an excellent candidate for an objective, unobtrusive measure of emotion. True stress was successfully induced, using two storytelling sessions performed by 25 patients suffering from a stress disorder. When reading either a happy or a sad story, different stress levels were reported using the Subjective Unit of Distress (SUD). A linear regression model consisting of the high-frequency energy, pitch, and zero crossings of the speech signal was able to explain 70% of the variance in the subjectively reported stress. The results demonstrate the feasibility of an objective measurement of stress in speech. As such, the foundation for an Artificial Therapeutic Agent is laid, capable of assisting therapists through an objective measurement of experienced stress.

Original language	Undefined
Title of host publication	Proceedings of the International Conference on Health Informatics, HealthInf 2011
Editors	V. Traver, A. Fred, J. Filipe, H. Gamboa
Place of Publication	Portugal
Publisher	INSTICC PRESS
Pages	357-363
Number of pages	7
ISBN (Print)	978-989-8425-34-8
Publication status	Published - 26 Jan 2011
Event	International Conference on Health Informatics, Healthinf 2011 - Rome, Italy Duration: 26 Jan 2011 → 29 Jan 2011

Publication series

Name
Publisher	INSTICC Press

Conference

Conference	International Conference on Health Informatics, Healthinf 2011
Period	26/01/11 → 29/01/11
Other	26-29 Jan 2011

Keywords

METIS-277522
IR-75881
Model
Agent
Stress
HMI-HF: Human Factors
Psychiatry
Diagnosis
EWI-19527
HMI-SLT: Speech and Language Technology
Speech

Access to Document

http://www.healthinf.biostec.org/

Cite this

@inproceedings{26ed57edbc394188ae7a988d6ac53566,

title = "Towards an artificial therapy assistant: Measuring excessive stress from speech",

abstract = "The measurement of (excessive) stress is still a challenging endeavor. Most tools rely on either introspection or expert opinion and are, therefore, often less reliable or a burden on the patient. An objective method could relieve these problems and, consequently, assist diagnostics. Speech was considered an excellent candidate for an objective, unobtrusive measure of emotion. True stress was successfully induced, using two storytelling sessions performed by 25 patients suffering from a stress disorder. When reading either a happy or a sad story, different stress levels were reported using the Subjective Unit of Distress (SUD). A linear regression model consisting of the high-frequency energy, pitch, and zero crossings of the speech signal was able to explain 70% of the variance in the subjectively reported stress. The results demonstrate the feasibility of an objective measurement of stress in speech. As such, the foundation for an Artificial Therapeutic Agent is laid, capable of assisting therapists through an objective measurement of experienced stress.",

keywords = "METIS-277522, IR-75881, Model, Agent, Stress, HMI-HF: Human Factors, Psychiatry, Diagnosis, EWI-19527, HMI-SLT: Speech and Language Technology, Speech",

author = "{van der Sluis}, Frans and {van den Broek}, Egon and Ton Dijkstra",

year = "2011",

month = jan,

day = "26",

language = "Undefined",

isbn = "978-989-8425-34-8",

publisher = "INSTICC PRESS",

pages = "357--363",

editor = "V. Traver and A. Fred and J. Filipe and H. Gamboa",

booktitle = "Proceedings of the International Conference on Health Informatics, HealthInf 2011",

note = "International Conference on Health Informatics, Healthinf 2011 ; Conference date: 26-01-2011 Through 29-01-2011",

}

van der Sluis, F, van den Broek, E & Dijkstra, T 2011, Towards an artificial therapy assistant: Measuring excessive stress from speech. in V Traver, A Fred, J Filipe & H Gamboa (eds), Proceedings of the International Conference on Health Informatics, HealthInf 2011. INSTICC PRESS, Portugal, pp. 357-363, International Conference on Health Informatics, Healthinf 2011, 26/01/11. <http://www.healthinf.biostec.org/>

Towards an artificial therapy assistant: Measuring excessive stress from speech. / van der Sluis, Frans; van den Broek, Egon; Dijkstra, Ton.
Proceedings of the International Conference on Health Informatics, HealthInf 2011. ed. / V. Traver; A. Fred; J. Filipe; H. Gamboa. Portugal: INSTICC PRESS, 2011. p. 357-363.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Towards an artificial therapy assistant: Measuring excessive stress from speech

AU - van der Sluis, Frans

AU - van den Broek, Egon

AU - Dijkstra, Ton

PY - 2011/1/26

Y1 - 2011/1/26

N2 - The measurement of (excessive) stress is still a challenging endeavor. Most tools rely on either introspection or expert opinion and are, therefore, often less reliable or a burden on the patient. An objective method could relieve these problems and, consequently, assist diagnostics. Speech was considered an excellent candidate for an objective, unobtrusive measure of emotion. True stress was successfully induced, using two storytelling sessions performed by 25 patients suffering from a stress disorder. When reading either a happy or a sad story, different stress levels were reported using the Subjective Unit of Distress (SUD). A linear regression model consisting of the high-frequency energy, pitch, and zero crossings of the speech signal was able to explain 70% of the variance in the subjectively reported stress. The results demonstrate the feasibility of an objective measurement of stress in speech. As such, the foundation for an Artificial Therapeutic Agent is laid, capable of assisting therapists through an objective measurement of experienced stress.

AB - The measurement of (excessive) stress is still a challenging endeavor. Most tools rely on either introspection or expert opinion and are, therefore, often less reliable or a burden on the patient. An objective method could relieve these problems and, consequently, assist diagnostics. Speech was considered an excellent candidate for an objective, unobtrusive measure of emotion. True stress was successfully induced, using two storytelling sessions performed by 25 patients suffering from a stress disorder. When reading either a happy or a sad story, different stress levels were reported using the Subjective Unit of Distress (SUD). A linear regression model consisting of the high-frequency energy, pitch, and zero crossings of the speech signal was able to explain 70% of the variance in the subjectively reported stress. The results demonstrate the feasibility of an objective measurement of stress in speech. As such, the foundation for an Artificial Therapeutic Agent is laid, capable of assisting therapists through an objective measurement of experienced stress.

KW - METIS-277522

KW - IR-75881

KW - Model

KW - Agent

KW - Stress

KW - HMI-HF: Human Factors

KW - Psychiatry

KW - Diagnosis

KW - EWI-19527

KW - HMI-SLT: Speech and Language Technology

KW - Speech

M3 - Conference contribution

SN - 978-989-8425-34-8

SP - 357

EP - 363

BT - Proceedings of the International Conference on Health Informatics, HealthInf 2011

A2 - Traver, V.

A2 - Fred, A.

A2 - Filipe, J.

A2 - Gamboa, H.

PB - INSTICC PRESS

CY - Portugal

T2 - International Conference on Health Informatics, Healthinf 2011

Y2 - 26 January 2011 through 29 January 2011

ER -