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

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-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 languageEnglish
Title of host publicationGCCE 2023 - 2023 IEEE 12th Global Conference on Consumer Electronics
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages603-605
Number of pages3
ISBN (Electronic)9798350340181
DOIs
Publication statusPublished - 2023
Event12th IEEE Global Conference on Consumer Electronics, GCCE 2023 - Nara, Japan
Duration: 10 Oct 202313 Oct 2023

Publication series

NameGCCE 2023 - 2023 IEEE 12th Global Conference on Consumer Electronics

Conference

Conference12th IEEE Global Conference on Consumer Electronics, GCCE 2023
Country/TerritoryJapan
CityNara
Period10/10/2313/10/23

Keywords

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

Fingerprint

Dive into the research topics of 'An End-to-End Model for Speech-based Somatisation Disorder Detection'. Together they form a unique fingerprint.

Cite this