An End-to-End Model for Speech-based Somatisation Disorder Detection

Runze Ge; Zhihua Wang; Zhonghao Zhao; Kun Qian; Bin Hu; Björn W. Schuller; Yoshiharu Yamamoto

doi:10.1109/GCCE59613.2023.10315568

An End-to-End Model for Speech-based Somatisation Disorder Detection

Runze Ge, Zhihua Wang, Zhonghao Zhao, Kun Qian, Bin Hu, Björn W. Schuller, Yoshiharu Yamamoto

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

Abstract

Somatisation disorder is a chronic psychiatric disorder that often lacks medical explanation, which can cause more severe functional impairment and social difficulties. In non-invasive speech modalities, auxiliary diagnosis of somatisation disorder can be undertaken. In this contribution, we propose an end-to-end deep neural network that detects somatisation disorders from one-dimensional raw speech signals. Our study is based on the Shenzhen Somatisation Speech Corpus, using the Patient Health Questionnaire-15 as the evaluation scale. Moreover, ways to mitigate model overfitting are explored in this work. Our experimental results on the test set finally reach 58.4 % UAR in the binary classification task.

Original language	English
Title of host publication	GCCE 2023 - 2023 IEEE 12th Global Conference on Consumer Electronics
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	603-605
Number of pages	3
ISBN (Electronic)	9798350340181
DOIs	https://doi.org/10.1109/GCCE59613.2023.10315568
State	Published - 2023
Externally published	Yes
Event	12th IEEE Global Conference on Consumer Electronics, GCCE 2023 - Nara, Japan Duration: 10 Oct 2023 → 13 Oct 2023

Publication series

Name	GCCE 2023 - 2023 IEEE 12th Global Conference on Consumer Electronics

Conference

Conference	12th IEEE Global Conference on Consumer Electronics, GCCE 2023
Country/Territory	Japan
City	Nara
Period	10/10/23 → 13/10/23

Keywords

Affective Computing
Digital Health
End-to-End Learning
Somatisation Disorder Detection

Access to Document

10.1109/GCCE59613.2023.10315568

Cite this

Ge, R., Wang, Z., Zhao, Z., Qian, K., Hu, B., Schuller, B. W., & Yamamoto, Y. (2023). An End-to-End Model for Speech-based Somatisation Disorder Detection. In GCCE 2023 - 2023 IEEE 12th Global Conference on Consumer Electronics (pp. 603-605). (GCCE 2023 - 2023 IEEE 12th Global Conference on Consumer Electronics). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/GCCE59613.2023.10315568

@inproceedings{7569978e5f93423b847cd8321440697e,

title = "An End-to-End Model for Speech-based Somatisation Disorder Detection",

abstract = "Somatisation disorder is a chronic psychiatric disorder that often lacks medical explanation, which can cause more severe functional impairment and social difficulties. In non-invasive speech modalities, auxiliary diagnosis of somatisation disorder can be undertaken. In this contribution, we propose an end-to-end deep neural network that detects somatisation disorders from one-dimensional raw speech signals. Our study is based on the Shenzhen Somatisation Speech Corpus, using the Patient Health Questionnaire-15 as the evaluation scale. Moreover, ways to mitigate model overfitting are explored in this work. Our experimental results on the test set finally reach 58.4 % UAR in the binary classification task.",

keywords = "Affective Computing, Digital Health, End-to-End Learning, Somatisation Disorder Detection",

author = "Runze Ge and Zhihua Wang and Zhonghao Zhao and Kun Qian and Bin Hu and Schuller, {Bj{\"o}rn W.} and Yoshiharu Yamamoto",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 12th IEEE Global Conference on Consumer Electronics, GCCE 2023 ; Conference date: 10-10-2023 Through 13-10-2023",

year = "2023",

doi = "10.1109/GCCE59613.2023.10315568",

language = "English",

series = "GCCE 2023 - 2023 IEEE 12th Global Conference on Consumer Electronics",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "603--605",

booktitle = "GCCE 2023 - 2023 IEEE 12th Global Conference on Consumer Electronics",

}

Ge, R, Wang, Z, Zhao, Z, Qian, K, Hu, B, Schuller, BW & Yamamoto, Y 2023, An End-to-End Model for Speech-based Somatisation Disorder Detection. in GCCE 2023 - 2023 IEEE 12th Global Conference on Consumer Electronics. GCCE 2023 - 2023 IEEE 12th Global Conference on Consumer Electronics, Institute of Electrical and Electronics Engineers Inc., pp. 603-605, 12th IEEE Global Conference on Consumer Electronics, GCCE 2023, Nara, Japan, 10/10/23. https://doi.org/10.1109/GCCE59613.2023.10315568

An End-to-End Model for Speech-based Somatisation Disorder Detection. / Ge, Runze; Wang, Zhihua; Zhao, Zhonghao et al.
GCCE 2023 - 2023 IEEE 12th Global Conference on Consumer Electronics. Institute of Electrical and Electronics Engineers Inc., 2023. p. 603-605 (GCCE 2023 - 2023 IEEE 12th Global Conference on Consumer Electronics).

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

TY - GEN

T1 - An End-to-End Model for Speech-based Somatisation Disorder Detection

AU - Ge, Runze

AU - Wang, Zhihua

AU - Zhao, Zhonghao

AU - Qian, Kun

AU - Hu, Bin

AU - Schuller, Björn W.

AU - Yamamoto, Yoshiharu

PY - 2023

Y1 - 2023

N2 - Somatisation disorder is a chronic psychiatric disorder that often lacks medical explanation, which can cause more severe functional impairment and social difficulties. In non-invasive speech modalities, auxiliary diagnosis of somatisation disorder can be undertaken. In this contribution, we propose an end-to-end deep neural network that detects somatisation disorders from one-dimensional raw speech signals. Our study is based on the Shenzhen Somatisation Speech Corpus, using the Patient Health Questionnaire-15 as the evaluation scale. Moreover, ways to mitigate model overfitting are explored in this work. Our experimental results on the test set finally reach 58.4 % UAR in the binary classification task.

AB - Somatisation disorder is a chronic psychiatric disorder that often lacks medical explanation, which can cause more severe functional impairment and social difficulties. In non-invasive speech modalities, auxiliary diagnosis of somatisation disorder can be undertaken. In this contribution, we propose an end-to-end deep neural network that detects somatisation disorders from one-dimensional raw speech signals. Our study is based on the Shenzhen Somatisation Speech Corpus, using the Patient Health Questionnaire-15 as the evaluation scale. Moreover, ways to mitigate model overfitting are explored in this work. Our experimental results on the test set finally reach 58.4 % UAR in the binary classification task.

KW - Affective Computing

KW - Digital Health

KW - End-to-End Learning

KW - Somatisation Disorder Detection

UR - http://www.scopus.com/inward/record.url?scp=85179762215&partnerID=8YFLogxK

U2 - 10.1109/GCCE59613.2023.10315568

DO - 10.1109/GCCE59613.2023.10315568

M3 - Conference contribution

AN - SCOPUS:85179762215

T3 - GCCE 2023 - 2023 IEEE 12th Global Conference on Consumer Electronics

SP - 603

EP - 605

BT - GCCE 2023 - 2023 IEEE 12th Global Conference on Consumer Electronics

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 12th IEEE Global Conference on Consumer Electronics, GCCE 2023

Y2 - 10 October 2023 through 13 October 2023

ER -

Ge R, Wang Z, Zhao Z, Qian K, Hu B, Schuller BW et al. An End-to-End Model for Speech-based Somatisation Disorder Detection. In GCCE 2023 - 2023 IEEE 12th Global Conference on Consumer Electronics. Institute of Electrical and Electronics Engineers Inc. 2023. p. 603-605. (GCCE 2023 - 2023 IEEE 12th Global Conference on Consumer Electronics). doi: 10.1109/GCCE59613.2023.10315568

An End-to-End Model for Speech-based Somatisation Disorder Detection

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this