Automatic Detection of Stress from Speech in the Trier Social Stress Test
For behavioral researchers and clinicians, this work demonstrates that speech can serve as an unobtrusive indicator of stress, though the results are incremental given the use of existing methods on a new dataset.
This study used speech data from 50 participants in the Trier Social Stress Test to automatically detect stress, achieving performance significantly above baseline, and partially predicted physiological and affective stress responses from acoustic-prosodic features.
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.