VoStress – Voice-based Detection of Acute Psychosocial Stress

Oesten M, Richer R, Abel L, Rohleder N, Eskofier B (2023)

Publication Language: English

Publication Type: Conference contribution, Original article

Publication year: 2023

Publisher: IEEE

Conference Proceedings Title: 2023 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI)

Event location: Pittsburgh US

URI: https://www.mad.tf.fau.de/files/2023/12/oesten23_stress_detection_voice.pdf

DOI: 10.1109/BHI58575.2023.10313458

Abstract

Current stress assessment methods include self-reports and biomarkers which are evaluated in often complex, laboratory procedures. Due to that investigating new indicators for acute stress is crucial for the development of automatic stress detection systems. A promising extension might be provided by investigating speech, which has been shown to be affected by negative emotions and threatening situations. For that reason, we extracted verbal acoustics from audio data collected during a study where N=21 participants underwent the Trier Social Stress Test (TSST), the gold standard for laboratory stress induction, and a stress-free control condition (friendly-TSST) while concurrently collecting cortisol via saliva samples to assess the biological response to stress. Our results show that acute stress leads to significant (p < 0.05) alterations of acoustic features. A stepwise backward multiple linear regression model explained 58.8 % of the variance of the maximum cortisol increase. In addition to that, we performed classification experiments that distinguished stress from non-stress situations with an accuracy of 80.0 ± 12.7 %. While further research is needed to validate our approach, we are convinced that the information extracted from speech can be a valuable indicator for automatic stress detection systems and can even predict the biological response to stress situations.

Authors with CRIS profile

Marie Oesten Machine Learning and Data Analytics Lab Robert Richer Machine Learning and Data Analytics Lab Luca Abel Machine Learning and Data Analytics Lab Nicolas Rohleder Lehrstuhl für Gesundheitspsychologie Björn Eskofier Machine Learning and Data Analytics Lab

Additional Organisation(s)

Sonderforschungsbereich 1483/1 Empathokinästhetische Sensorik – Sensortechniken und Datenanalyseverfahren zur empathokinästhetischen Modellbildung und Zustandsbestimmung

Related research project(s)

Berührungslose Messung von Stress, seiner Determinanten und Konsequenzen (SFB 1483 EmpkinS D03) Empatho-Kinaesthetic Sensor Technology (SFB 1483 EmpkinS) July 1, 2021 - June 30, 2025

How to cite

APA:

Oesten, M., Richer, R., Abel, L., Rohleder, N., & Eskofier, B. (2023). VoStress – Voice-based Detection of Acute Psychosocial Stress. In 2023 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI). Pittsburgh, US: IEEE.

MLA:

Oesten, Marie, et al. "VoStress – Voice-based Detection of Acute Psychosocial Stress." Proceedings of the 2023 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI), Pittsburgh IEEE, 2023.

BibTeX: Download