Characterising Depressed Speech for Classification

Sharifa Alghowinem, Roland GOECKE, Michael WAGNER, Julien Epps, Gordon Parker, Michael Breakspear

Research output: A Conference proceeding or a Chapter in BookConference contribution

16 Citations (Scopus)

Abstract

Depression is a serious psychiatric disorder that affects mood, thoughts, and the ability to function in everyday life. This paper investigates the characteristics of depressed speech for the purpose of automatic classification by analysing the effect of different speech features on the classification results. We analysed voiced, unvoiced and mixed speech in order to gain a better understanding of depressed speech and to bridge the gap between physiological and affective computing studies. This understanding may ultimately lead to an objective affective sensing system that supports clinicians in their diagnosis and monitoring of clinical depression. The characteristics of depressed speech were statistically analysed using ANOVA and linked to their classification results using GMM and SVM. Features were extracted and classified over speech utterances of 30 clinically depressed patients against 30 controls (both gender-matched) in a speaker-independent manner. Most feature classification results were consistent with their statistical characteristics, providing a link between physiological and affective computing studies. The classification results from low-level features were slightly better than the statistical functional features, which indicates a loss of information in the latter. We found that both mixed and unvoiced speech were as useful in detecting depression as voiced speech, if not better.
Original languageEnglish
Title of host publication14th Annual Conference of the International Speech Communication Association Interspeech 2013
EditorsFrederic Bimbot, Cecile Fougeron, Francois Pellegrino
Place of PublicationLyon, France
PublisherInternational Speech Communication Association
Pages2534-2538
Number of pages5
Publication statusPublished - 2013
Event14th Annual Conference of the International Speech Communication Association Interspeech 2013 - Lyon, Lyon, France
Duration: 25 Aug 201329 Aug 2013

Conference

Conference14th Annual Conference of the International Speech Communication Association Interspeech 2013
Abbreviated titleINTERSPEECH 2013
CountryFrance
CityLyon
Period25/08/1329/08/13

Fingerprint

Analysis of variance (ANOVA)
Monitoring
Psychiatry

Cite this

Alghowinem, S., GOECKE, R., WAGNER, M., Epps, J., Parker, G., & Breakspear, M. (2013). Characterising Depressed Speech for Classification. In F. Bimbot, C. Fougeron, & F. Pellegrino (Eds.), 14th Annual Conference of the International Speech Communication Association Interspeech 2013 (pp. 2534-2538). Lyon, France: International Speech Communication Association.
Alghowinem, Sharifa ; GOECKE, Roland ; WAGNER, Michael ; Epps, Julien ; Parker, Gordon ; Breakspear, Michael. / Characterising Depressed Speech for Classification. 14th Annual Conference of the International Speech Communication Association Interspeech 2013. editor / Frederic Bimbot ; Cecile Fougeron ; Francois Pellegrino. Lyon, France : International Speech Communication Association, 2013. pp. 2534-2538
@inproceedings{9b7e83fb7f314260a5a1644d5210f44f,
title = "Characterising Depressed Speech for Classification",
abstract = "Depression is a serious psychiatric disorder that affects mood, thoughts, and the ability to function in everyday life. This paper investigates the characteristics of depressed speech for the purpose of automatic classification by analysing the effect of different speech features on the classification results. We analysed voiced, unvoiced and mixed speech in order to gain a better understanding of depressed speech and to bridge the gap between physiological and affective computing studies. This understanding may ultimately lead to an objective affective sensing system that supports clinicians in their diagnosis and monitoring of clinical depression. The characteristics of depressed speech were statistically analysed using ANOVA and linked to their classification results using GMM and SVM. Features were extracted and classified over speech utterances of 30 clinically depressed patients against 30 controls (both gender-matched) in a speaker-independent manner. Most feature classification results were consistent with their statistical characteristics, providing a link between physiological and affective computing studies. The classification results from low-level features were slightly better than the statistical functional features, which indicates a loss of information in the latter. We found that both mixed and unvoiced speech were as useful in detecting depression as voiced speech, if not better.",
keywords = "depression, speech characteristics, mood classification",
author = "Sharifa Alghowinem and Roland GOECKE and Michael WAGNER and Julien Epps and Gordon Parker and Michael Breakspear",
year = "2013",
language = "English",
pages = "2534--2538",
editor = "Frederic Bimbot and Cecile Fougeron and Francois Pellegrino",
booktitle = "14th Annual Conference of the International Speech Communication Association Interspeech 2013",
publisher = "International Speech Communication Association",

}

Alghowinem, S, GOECKE, R, WAGNER, M, Epps, J, Parker, G & Breakspear, M 2013, Characterising Depressed Speech for Classification. in F Bimbot, C Fougeron & F Pellegrino (eds), 14th Annual Conference of the International Speech Communication Association Interspeech 2013. International Speech Communication Association, Lyon, France, pp. 2534-2538, 14th Annual Conference of the International Speech Communication Association Interspeech 2013, Lyon, France, 25/08/13.

Characterising Depressed Speech for Classification. / Alghowinem, Sharifa; GOECKE, Roland; WAGNER, Michael; Epps, Julien; Parker, Gordon; Breakspear, Michael.

14th Annual Conference of the International Speech Communication Association Interspeech 2013. ed. / Frederic Bimbot; Cecile Fougeron; Francois Pellegrino. Lyon, France : International Speech Communication Association, 2013. p. 2534-2538.

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - Characterising Depressed Speech for Classification

AU - Alghowinem, Sharifa

AU - GOECKE, Roland

AU - WAGNER, Michael

AU - Epps, Julien

AU - Parker, Gordon

AU - Breakspear, Michael

PY - 2013

Y1 - 2013

N2 - Depression is a serious psychiatric disorder that affects mood, thoughts, and the ability to function in everyday life. This paper investigates the characteristics of depressed speech for the purpose of automatic classification by analysing the effect of different speech features on the classification results. We analysed voiced, unvoiced and mixed speech in order to gain a better understanding of depressed speech and to bridge the gap between physiological and affective computing studies. This understanding may ultimately lead to an objective affective sensing system that supports clinicians in their diagnosis and monitoring of clinical depression. The characteristics of depressed speech were statistically analysed using ANOVA and linked to their classification results using GMM and SVM. Features were extracted and classified over speech utterances of 30 clinically depressed patients against 30 controls (both gender-matched) in a speaker-independent manner. Most feature classification results were consistent with their statistical characteristics, providing a link between physiological and affective computing studies. The classification results from low-level features were slightly better than the statistical functional features, which indicates a loss of information in the latter. We found that both mixed and unvoiced speech were as useful in detecting depression as voiced speech, if not better.

AB - Depression is a serious psychiatric disorder that affects mood, thoughts, and the ability to function in everyday life. This paper investigates the characteristics of depressed speech for the purpose of automatic classification by analysing the effect of different speech features on the classification results. We analysed voiced, unvoiced and mixed speech in order to gain a better understanding of depressed speech and to bridge the gap between physiological and affective computing studies. This understanding may ultimately lead to an objective affective sensing system that supports clinicians in their diagnosis and monitoring of clinical depression. The characteristics of depressed speech were statistically analysed using ANOVA and linked to their classification results using GMM and SVM. Features were extracted and classified over speech utterances of 30 clinically depressed patients against 30 controls (both gender-matched) in a speaker-independent manner. Most feature classification results were consistent with their statistical characteristics, providing a link between physiological and affective computing studies. The classification results from low-level features were slightly better than the statistical functional features, which indicates a loss of information in the latter. We found that both mixed and unvoiced speech were as useful in detecting depression as voiced speech, if not better.

KW - depression

KW - speech characteristics

KW - mood classification

M3 - Conference contribution

SP - 2534

EP - 2538

BT - 14th Annual Conference of the International Speech Communication Association Interspeech 2013

A2 - Bimbot, Frederic

A2 - Fougeron, Cecile

A2 - Pellegrino, Francois

PB - International Speech Communication Association

CY - Lyon, France

ER -

Alghowinem S, GOECKE R, WAGNER M, Epps J, Parker G, Breakspear M. Characterising Depressed Speech for Classification. In Bimbot F, Fougeron C, Pellegrino F, editors, 14th Annual Conference of the International Speech Communication Association Interspeech 2013. Lyon, France: International Speech Communication Association. 2013. p. 2534-2538