Distinct Prosodic Correlates for Nine Dimensions of Mental Health Symptoms

Maria Wolters; Alex Cohen; Kristin Nicodemus

Distinct Prosodic Correlates for Nine Dimensions of Mental Health Symptoms

Maria Wolters, Alex Cohen, Kristin Nicodemus

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

People’s lived experience of mental illness often includes symptoms associated with several different conditions. The Brief Symptom Inventory (BSI) is a well validated tool for collecting symptom self-reports that covers nine dimensions: depression, anxiety, phobia, paranoia, psychosis, OCD, hostility, somatisation, and interpersonal. In this paper, we investigate to what extent these dimensions are reflected in prosody. Prosody was characterised using five core principal components (PC) derived from GeMAPS analysis of a data set from 8 studies (14907 sound files, 990 participants). We used the data from a subset of 317
participants (5967 sound files, 4 studies) who had completed the BSI. Each BSI dimension shows a distinct pattern of correlations between the number of symptoms reported and our five PCs, but these patterns differ
when comparing undergraduates (more Caucasians, more females) and a patient sample (more African-Americans, more males). We conclude that speech corpora for mental health studies need better demographic balance.

Original language	English
Title of host publication	Proceedings of the 19th International Congress of Phonetic Sciences ICPhS 2019
Subtitle of host publication	5-9 August 2019, Melbourne, Australia
Editors	Sasha Calhoun, Paola Escudero, Marija Tabain, Paul Warren
Place of Publication	Canberra, Australia: Australasian Speech Science and Technology Association Inc.
Publisher	Australian Speech Science & Technology Association Inc
Pages	3001-3005
Number of pages	5
ISBN (Print)	978-0-646-800069-1
Publication status	Published - 31 Aug 2019
Event	19th International Congress of Phonetic Sciences - Melbourne, Australia Duration: 5 Aug 2019 → 9 Aug 2019 https://www.icphs2019.org/

Conference

Conference	19th International Congress of Phonetic Sciences
Abbreviated title	ICPhS 2019
Country/Territory	Australia
City	Melbourne
Period	5/08/19 → 9/08/19
Internet address	https://www.icphs2019.org/

Access to Document

Distinct Prosodic Correlates_WOLTERS_DoA150219_AFVAccepted author manuscript, 113 KBLicence: All Rights Reserved

https://assta.org/proceedings/ICPhS2019/Licence: All Rights Reserved

ATI Faculty Fellowship
Wolters, M. (Principal Investigator)
UK-based charities
1/09/16 → 31/08/20
Project: Research

Cite this

Wolters, M., Cohen, A., & Nicodemus, K. (2019). Distinct Prosodic Correlates for Nine Dimensions of Mental Health Symptoms. In S. Calhoun, P. Escudero, M. Tabain, & P. Warren (Eds.), Proceedings of the 19th International Congress of Phonetic Sciences ICPhS 2019: 5-9 August 2019, Melbourne, Australia (pp. 3001-3005). Australian Speech Science & Technology Association Inc. https://assta.org/proceedings/ICPhS2019/

Wolters, Maria ; Cohen, Alex ; Nicodemus, Kristin. / Distinct Prosodic Correlates for Nine Dimensions of Mental Health Symptoms. Proceedings of the 19th International Congress of Phonetic Sciences ICPhS 2019: 5-9 August 2019, Melbourne, Australia. editor / Sasha Calhoun ; Paola Escudero ; Marija Tabain ; Paul Warren. Canberra, Australia: Australasian Speech Science and Technology Association Inc. : Australian Speech Science & Technology Association Inc, 2019. pp. 3001-3005

@inproceedings{14be0845292b4467982b874dd8962dd7,

title = "Distinct Prosodic Correlates for Nine Dimensions of Mental Health Symptoms",

abstract = "People{\textquoteright}s lived experience of mental illness often includes symptoms associated with several different conditions. The Brief Symptom Inventory (BSI) is a well validated tool for collecting symptom self-reports that covers nine dimensions: depression, anxiety, phobia, paranoia, psychosis, OCD, hostility, somatisation, and interpersonal. In this paper, we investigate to what extent these dimensions are reflected in prosody. Prosody was characterised using five core principal components (PC) derived from GeMAPS analysis of a data set from 8 studies (14907 sound files, 990 participants). We used the data from a subset of 317 participants (5967 sound files, 4 studies) who had completed the BSI. Each BSI dimension shows a distinct pattern of correlations between the number of symptoms reported and our five PCs, but these patterns differwhen comparing undergraduates (more Caucasians, more females) and a patient sample (more African-Americans, more males). We conclude that speech corpora for mental health studies need better demographic balance.",

author = "Maria Wolters and Alex Cohen and Kristin Nicodemus",

year = "2019",

month = aug,

day = "31",

language = "English",

isbn = "978-0-646-800069-1",

pages = "3001--3005",

editor = "Sasha Calhoun and Paola Escudero and Marija Tabain and Paul Warren",

booktitle = "Proceedings of the 19th International Congress of Phonetic Sciences ICPhS 2019",

publisher = "Australian Speech Science & Technology Association Inc",

note = "19th International Congress of Phonetic Sciences, ICPhS 2019 ; Conference date: 05-08-2019 Through 09-08-2019",

url = "https://www.icphs2019.org/",

}

Wolters, M, Cohen, A & Nicodemus, K 2019, Distinct Prosodic Correlates for Nine Dimensions of Mental Health Symptoms. in S Calhoun, P Escudero, M Tabain & P Warren (eds), Proceedings of the 19th International Congress of Phonetic Sciences ICPhS 2019: 5-9 August 2019, Melbourne, Australia. Australian Speech Science & Technology Association Inc, Canberra, Australia: Australasian Speech Science and Technology Association Inc., pp. 3001-3005, 19th International Congress of Phonetic Sciences, Melbourne, Victoria, Australia, 5/08/19. <https://assta.org/proceedings/ICPhS2019/>

Distinct Prosodic Correlates for Nine Dimensions of Mental Health Symptoms. / Wolters, Maria; Cohen, Alex; Nicodemus, Kristin.
Proceedings of the 19th International Congress of Phonetic Sciences ICPhS 2019: 5-9 August 2019, Melbourne, Australia. ed. / Sasha Calhoun; Paola Escudero; Marija Tabain; Paul Warren. Canberra, Australia: Australasian Speech Science and Technology Association Inc.: Australian Speech Science & Technology Association Inc, 2019. p. 3001-3005.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Distinct Prosodic Correlates for Nine Dimensions of Mental Health Symptoms

AU - Wolters, Maria

AU - Cohen, Alex

AU - Nicodemus, Kristin

PY - 2019/8/31

Y1 - 2019/8/31

N2 - People’s lived experience of mental illness often includes symptoms associated with several different conditions. The Brief Symptom Inventory (BSI) is a well validated tool for collecting symptom self-reports that covers nine dimensions: depression, anxiety, phobia, paranoia, psychosis, OCD, hostility, somatisation, and interpersonal. In this paper, we investigate to what extent these dimensions are reflected in prosody. Prosody was characterised using five core principal components (PC) derived from GeMAPS analysis of a data set from 8 studies (14907 sound files, 990 participants). We used the data from a subset of 317 participants (5967 sound files, 4 studies) who had completed the BSI. Each BSI dimension shows a distinct pattern of correlations between the number of symptoms reported and our five PCs, but these patterns differwhen comparing undergraduates (more Caucasians, more females) and a patient sample (more African-Americans, more males). We conclude that speech corpora for mental health studies need better demographic balance.

AB - People’s lived experience of mental illness often includes symptoms associated with several different conditions. The Brief Symptom Inventory (BSI) is a well validated tool for collecting symptom self-reports that covers nine dimensions: depression, anxiety, phobia, paranoia, psychosis, OCD, hostility, somatisation, and interpersonal. In this paper, we investigate to what extent these dimensions are reflected in prosody. Prosody was characterised using five core principal components (PC) derived from GeMAPS analysis of a data set from 8 studies (14907 sound files, 990 participants). We used the data from a subset of 317 participants (5967 sound files, 4 studies) who had completed the BSI. Each BSI dimension shows a distinct pattern of correlations between the number of symptoms reported and our five PCs, but these patterns differwhen comparing undergraduates (more Caucasians, more females) and a patient sample (more African-Americans, more males). We conclude that speech corpora for mental health studies need better demographic balance.

M3 - Conference contribution

SN - 978-0-646-800069-1

SP - 3001

EP - 3005

BT - Proceedings of the 19th International Congress of Phonetic Sciences ICPhS 2019

A2 - Calhoun, Sasha

A2 - Escudero, Paola

A2 - Tabain, Marija

A2 - Warren, Paul

PB - Australian Speech Science & Technology Association Inc

CY - Canberra, Australia: Australasian Speech Science and Technology Association Inc.

T2 - 19th International Congress of Phonetic Sciences

Y2 - 5 August 2019 through 9 August 2019

ER -

Wolters M, Cohen A, Nicodemus K. Distinct Prosodic Correlates for Nine Dimensions of Mental Health Symptoms. In Calhoun S, Escudero P, Tabain M, Warren P, editors, Proceedings of the 19th International Congress of Phonetic Sciences ICPhS 2019: 5-9 August 2019, Melbourne, Australia. Canberra, Australia: Australasian Speech Science and Technology Association Inc.: Australian Speech Science & Technology Association Inc. 2019. p. 3001-3005

Distinct Prosodic Correlates for Nine Dimensions of Mental Health Symptoms

Abstract

Conference

Access to Document

Fingerprint

Projects

ATI Faculty Fellowship

Cite this