Cross-Cultural Depression Recognition from Vocal Biomarkers

Sharifa Alghowinem, Roland GOECKE, Julien Epps, Michael WAGNER, Jeffrey Cohn

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

9 Citations (Scopus)
2 Downloads (Pure)

Abstract

No studies have investigated cross-cultural and cross-language characteristics of depressed speech. We investigated the generalisability of a vocal biomarker-based approach to depression detection in clinical interviews recorded in three countries (Australia, the USA and Germany), two languages (German and English) and different accents (Australian and American). Several approaches to training and testing within and between datasets were evaluated. Using the same experimental protocol separately within each dataset, (cross-classification) accuracy was high. Combining datasets, high accuracy was high again and consistent across language, recording environment, and culture. Training and testing between datasets, however, attenuated accuracy. These finding emphasize the importance of heterogeneous training sets for robust depression detection.
Original languageEnglish
Title of host publicationProceedings of Interspeech 2016
EditorsNelson Morgan
Place of PublicationSan Francisco
PublisherInternational Speech Communication Association (ISCA)
Pages1943-1947
Number of pages5
Volume08-12-September-2016
ISBN (Print)9781510833135
DOIs
Publication statusPublished - 2016
EventInterspeech 2016 - San Francisco, San Francisco, United States
Duration: 8 Sep 201612 Sep 2016
http://www.interspeech2016.org/ (Conference website)

Publication series

NameProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
ISSN (Print)2308-457X

Conference

ConferenceInterspeech 2016
CountryUnited States
CitySan Francisco
Period8/09/1612/09/16
OtherInterspeech 2016 will be organized around the topic: Understanding Speech Processing in Humans and Machines. The event will be held in the Hyatt Regency San Francisco hotel in the beautiful San Francisco, California. Interspeech 2016 emphasizes an interdisciplinary approach covering all aspects of speech science and technology spanning basic theories to applications. In addition to regular oral and poster sessions, the conference will also feature plenary talks by internationally renowned experts, tutorials, special sessions, show & tell sessions, and exhibits. A number of satellite events will take place immediately before and after the conference
Internet address

Fingerprint

biomarker
detection

Cite this

Alghowinem, S., GOECKE, R., Epps, J., WAGNER, M., & Cohn, J. (2016). Cross-Cultural Depression Recognition from Vocal Biomarkers. In N. Morgan (Ed.), Proceedings of Interspeech 2016 (Vol. 08-12-September-2016, pp. 1943-1947). (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH). San Francisco: International Speech Communication Association (ISCA). https://doi.org/10.21437/Interspeech.2016-1339
Alghowinem, Sharifa ; GOECKE, Roland ; Epps, Julien ; WAGNER, Michael ; Cohn, Jeffrey. / Cross-Cultural Depression Recognition from Vocal Biomarkers. Proceedings of Interspeech 2016. editor / Nelson Morgan. Vol. 08-12-September-2016 San Francisco : International Speech Communication Association (ISCA), 2016. pp. 1943-1947 (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH).
@inproceedings{dac193ad79fb46eba64993ed29e070af,
title = "Cross-Cultural Depression Recognition from Vocal Biomarkers",
abstract = "No studies have investigated cross-cultural and cross-language characteristics of depressed speech. We investigated the generalisability of a vocal biomarker-based approach to depression detection in clinical interviews recorded in three countries (Australia, the USA and Germany), two languages (German and English) and different accents (Australian and American). Several approaches to training and testing within and between datasets were evaluated. Using the same experimental protocol separately within each dataset, (cross-classification) accuracy was high. Combining datasets, high accuracy was high again and consistent across language, recording environment, and culture. Training and testing between datasets, however, attenuated accuracy. These finding emphasize the importance of heterogeneous training sets for robust depression detection.",
keywords = "cross-cultural-depression-recognition, vocal-biomarkers",
author = "Sharifa Alghowinem and Roland GOECKE and Julien Epps and Michael WAGNER and Jeffrey Cohn",
year = "2016",
doi = "10.21437/Interspeech.2016-1339",
language = "English",
isbn = "9781510833135",
volume = "08-12-September-2016",
series = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",
publisher = "International Speech Communication Association (ISCA)",
pages = "1943--1947",
editor = "Nelson Morgan",
booktitle = "Proceedings of Interspeech 2016",

}

Alghowinem, S, GOECKE, R, Epps, J, WAGNER, M & Cohn, J 2016, Cross-Cultural Depression Recognition from Vocal Biomarkers. in N Morgan (ed.), Proceedings of Interspeech 2016. vol. 08-12-September-2016, Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, International Speech Communication Association (ISCA), San Francisco, pp. 1943-1947, Interspeech 2016, San Francisco, United States, 8/09/16. https://doi.org/10.21437/Interspeech.2016-1339

Cross-Cultural Depression Recognition from Vocal Biomarkers. / Alghowinem, Sharifa; GOECKE, Roland; Epps, Julien; WAGNER, Michael; Cohn, Jeffrey.

Proceedings of Interspeech 2016. ed. / Nelson Morgan. Vol. 08-12-September-2016 San Francisco : International Speech Communication Association (ISCA), 2016. p. 1943-1947 (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH).

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

TY - GEN

T1 - Cross-Cultural Depression Recognition from Vocal Biomarkers

AU - Alghowinem, Sharifa

AU - GOECKE, Roland

AU - Epps, Julien

AU - WAGNER, Michael

AU - Cohn, Jeffrey

PY - 2016

Y1 - 2016

N2 - No studies have investigated cross-cultural and cross-language characteristics of depressed speech. We investigated the generalisability of a vocal biomarker-based approach to depression detection in clinical interviews recorded in three countries (Australia, the USA and Germany), two languages (German and English) and different accents (Australian and American). Several approaches to training and testing within and between datasets were evaluated. Using the same experimental protocol separately within each dataset, (cross-classification) accuracy was high. Combining datasets, high accuracy was high again and consistent across language, recording environment, and culture. Training and testing between datasets, however, attenuated accuracy. These finding emphasize the importance of heterogeneous training sets for robust depression detection.

AB - No studies have investigated cross-cultural and cross-language characteristics of depressed speech. We investigated the generalisability of a vocal biomarker-based approach to depression detection in clinical interviews recorded in three countries (Australia, the USA and Germany), two languages (German and English) and different accents (Australian and American). Several approaches to training and testing within and between datasets were evaluated. Using the same experimental protocol separately within each dataset, (cross-classification) accuracy was high. Combining datasets, high accuracy was high again and consistent across language, recording environment, and culture. Training and testing between datasets, however, attenuated accuracy. These finding emphasize the importance of heterogeneous training sets for robust depression detection.

KW - cross-cultural-depression-recognition

KW - vocal-biomarkers

UR - http://www.scopus.com/inward/record.url?scp=84994291450&partnerID=8YFLogxK

U2 - 10.21437/Interspeech.2016-1339

DO - 10.21437/Interspeech.2016-1339

M3 - Conference contribution

SN - 9781510833135

VL - 08-12-September-2016

T3 - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

SP - 1943

EP - 1947

BT - Proceedings of Interspeech 2016

A2 - Morgan, Nelson

PB - International Speech Communication Association (ISCA)

CY - San Francisco

ER -

Alghowinem S, GOECKE R, Epps J, WAGNER M, Cohn J. Cross-Cultural Depression Recognition from Vocal Biomarkers. In Morgan N, editor, Proceedings of Interspeech 2016. Vol. 08-12-September-2016. San Francisco: International Speech Communication Association (ISCA). 2016. p. 1943-1947. (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH). https://doi.org/10.21437/Interspeech.2016-1339