Automatic Detection of Stress from Speech in the Trier Social Stress Test
2026-07-01 • Machine Learning
Machine Learning
AI summaryⓘ
The authors studied how to tell if someone is stressed by listening to their speech. They recorded 50 people speaking during a stressful test and a calm situation. Using computer methods, they could tell stressed speech from calm speech better than random guessing. They also found that certain voice features could partly predict physical and emotional signs of stress. Their work shows that speech can give clues about how stressed a person is without bothering them.
stress detectionspeech analysisTrier Social Stress Testmachine learningacoustic-prosodic featuresspeaker diarizationphysiological stressaffective stressbehavioral assessment
Authors
Hanna Drimalla, Wieland R. Cremer, Christine Kraus, Oliver T. Wolf
Abstract
Automatically detecting stress in speech provides an unobtrusive way to gain insights relevant to behavioral research or clinical assessment. This study investigates the automatic differentiation between a stressful and non-stressful situation, and the prediction of physiological and affective stress responses. Speech data was collected from 50 participants who either completed the Trier Social Stress Test (TSST) or a non-stressful control condition. With a processing pipeline that included speaker diarization and machine learning models, we achieved stress detection performance significantly above a mean baseline. Moreover, relevant physiological and affective stress responses were partially predictable from acoustic-prosodic features. Feature-importance analyses identified the most informative predictors contributing to model performance. The findings demonstrate that speech can serve as a meaningful and unobtrusive indicator of multiple dimensions of the human stress response.