scholarly journals An Evaluation of Speech-Based Recognition of Emotional and Physiological Markers of Stress

2021 ◽  
Vol 3 ◽  
Author(s):  
Alice Baird ◽  
Andreas Triantafyllopoulos ◽  
Sandra Zänkert ◽  
Sandra Ottl ◽  
Lukas Christ ◽  
...  

Life in modern societies is fast-paced and full of stress-inducing demands. The development of stress monitoring methods is a growing area of research due to the personal and economic advantages that timely detection provides. Studies have shown that speech-based features can be utilised to robustly predict several physiological markers of stress, including emotional state, continuous heart rate, and the stress hormone, cortisol. In this contribution, we extend previous works by the authors, utilising three German language corpora including more than 100 subjects undergoing a Trier Social Stress Test protocol. We present cross-corpus and transfer learning results which explore the efficacy of the speech signal to predict three physiological markers of stress—sequentially measured saliva-based cortisol, continuous heart rate as beats per minute (BPM), and continuous respiration. For this, we extract several features from audio as well as video and apply various machine learning architectures, including a temporal context-based Long Short-Term Memory Recurrent Neural Network (LSTM-RNN). For the task of predicting cortisol levels from speech, deep learning improves on results obtained by conventional support vector regression—yielding a Spearman correlation coefficient (ρ) of 0.770 and 0.698 for cortisol measurements taken 10 and 20 min after the stress period for the two corpora applicable—showing that audio features alone are sufficient for predicting cortisol, with audiovisual fusion to an extent improving such results. We also obtain a Root Mean Square Error (RMSE) of 38 and 22 BPM for continuous heart rate prediction on the two corpora where this information is available, and a normalised RMSE (NRMSE) of 0.120 for respiration prediction (−10: 10). Both of these continuous physiological signals show to be highly effective markers of stress (based on cortisol grouping analysis), both when available as ground truth and when predicted using speech. This contribution opens up new avenues for future exploration of these signals as proxies for stress in naturalistic settings.

2017 ◽  
Vol 29 (11) ◽  
pp. 1803-1816 ◽  
Author(s):  
Maheen Shermohammed ◽  
Pranjal H. Mehta ◽  
Joan Zhang ◽  
Cassandra M. Brandes ◽  
Luke J. Chang ◽  
...  

Cognitive reappraisal (CR) is regarded as an effective emotion regulation strategy. Acute stress, however, is believed to impair the functioning of prefrontal-based neural systems, which could result in lessened effectiveness of CR under stress. This study tested the behavioral and neurobiological impact of acute stress on CR. While undergoing fMRI, adult participants ( n = 54) passively viewed or used CR to regulate their response to negative and neutral pictures and provided ratings of their negative affect in response to each picture. Half of the participants experienced an fMRI-adapted acute psychosocial stress manipulation similar to the Trier Social Stress Test, and a control group received parallel manipulations without the stressful components. Relative to the control group, the stress group exhibited heightened stress as indexed by self-report, heart rate, and salivary cortisol throughout the scan. Contrary to our hypothesis, we found that reappraisal success was equivalent in the control and stress groups, as was electrodermal response to the pictures. Heart rate deceleration, a physiological response typically evoked by aversive pictures, was blunted in response to negative pictures and heightened in response to neutral pictures in the stress group. In the brain, we found weak evidence of stress-induced increases of reappraisal-related activity in parts of the PFC and left amygdala, but these relationships were statistically fragile. Together, these findings suggest that both the self-reported and neural effects of CR may be robust to at least moderate levels of stress, informing theoretical models of stress effects on cognition and emotion.


2015 ◽  
Vol 26 (5) ◽  
pp. 555-579 ◽  
Author(s):  
Anjana Bali ◽  
Amteshwar Singh Jaggi

AbstractStress is a state of threatened homeostasis during which a variety of adaptive processes are activated to produce physiological and behavioral changes. Stress induction methods are pivotal for understanding these physiological or pathophysiological changes in the body in response to stress. Furthermore, these methods are also important for the development of novel pharmacological agents for stress management. The well-described methods to induce stress in humans include the cold pressor test, Trier Social Stress Test, Montreal Imaging Stress Task, Maastricht Acute Stress Test, CO2 challenge test, Stroop test, Paced Auditory Serial Addition Task, noise stress, and Mannheim Multicomponent Stress Test. Stress assessment in humans is done by measuring biochemical markers such as cortisol, cortisol awakening response, dexamethasone suppression test, salivary α-amylase, plasma/urinary norepinephrine, norepinephrine spillover rate, and interleukins. Physiological and behavioral changes such as galvanic skin response, heart rate variability, pupil size, and muscle and/or skin sympathetic nerve activity (microneurography) and cardiovascular parameters such as heart rate, blood pressure, and self-reported anxiety are also monitored to assess stress response. This present review describes these commonly employed methods to induce stress in humans along with stress assessment methods.


2020 ◽  
Author(s):  
Qing Liu ◽  
Wenjuan Zhang

Abstract Background: The aim of the present study is to investigate the sex differences in stress reactivity to the Trier Social Stress Test (TSST) in a virtual reality(TSST-VR). Methods: Healthy young male (n = 30) and female (n = 30) undergraduates were randomly assigned to a psychosocial stress protocol (TSST) condition or to a non-stressful control condition (Placebo-TSST) under VR. Electrodermal activity (EDA), heart rate (HR) and heart rate variability (HRV) were measured throughout the study. The subjective scales of stress and emotion were also conducted. Results: The results showed that after VR, the stress group reported higher stress perceptions than the non-stress group. Compared with females, the males stronger EDA and higher HRV before the VR, and lower HR during VR as well as higher HRV after VR. The correlation between subjective and objective reactivity demonstrated that HRV during VR was negatively correlated to depression and negative affect. The HRV after VR was negatively correlated to the positive coping but was positively correlated to the depression. Conclusions: These findings suggest that the TSST-VR could be used as an available tool for testing gender differences to social stress induction in experimental settings. Compared with females, males were more sensitive to stress.


2020 ◽  
Author(s):  
Nicolás Francisco Narvaez Linares ◽  
Valérie Charron ◽  
Allison Ouimet ◽  
Patrick R. Labelle ◽  
Hélène Plamondon

Since its development in 1993, the Trier Social Stress Test (TSST) has been used widely as a psychosocial stress paradigm to activate the sympathetic nervous system and hypothalamic-pituitary-adrenal axis (HPAA) stress systems, stimulating physiological functions (e.g. heart rate) and cortisol secretion. Several methodological variations introduced over the years have led the scientific community to question replication between studies. In this systematic review, we used the Preferred Reporting Items of Systematic Reviews and Meta-Analysis (PRISMA) to synthesize procedure-related data available about the TSST protocol to highlight commonalities and differences across studies. We noted significant discrepancies across studies in how researchers applied the TSST protocol. In particular, we highlight variations in testing procedures (e.g., number of judges, initial number in the arithmetic task, time of the collected saliva samples for cortisol) and discuss possible misinterpretation in comparing findings from studies failing to control for variables or using a modified version from the original protocol. Further, we recommend that researchers use a standardized background questionnaire when using the TSST to identify factors that may influence physiological measurements in tandem with a summary of this review as a protocol guide. More systematic implementation and detailed reporting of TSST methodology will promote study replication, optimize comparison of findings, and foster an informed understanding of factors affecting responses to social stressors in healthy people and those with pathological conditions. Keywords: Trier Social Stress Test, Stress paradigm, Protocol, Systematic Review, Standardization


Psych ◽  
2021 ◽  
Vol 3 (2) ◽  
pp. 171-183
Author(s):  
Isabelle K. Sequeira ◽  
Addie S. Longmire ◽  
Naomi J. McKay

The Trier Social Stress Test (TSST) is a psychosocial stressor that effectively stimulates the stress response but is labor and time intensive. Although other psychological stressors are often used experimentally, none are known to comparably elevate stress. Two stressors that may potentially elevate stress are a singing task (ST) and unsolvable anagrams, but there are not enough data to support their effectiveness. In the current experiment, 53 undergraduate males and females (mean age = 21.9 years) were brought into the laboratory, and baseline blood pressure, heart rate, self-rated anxiety, and salivary cortisol were recorded. Then, participants were randomly assigned to one of three stress conditions: TSST (n = 24), ST (n = 14), or an unsolvable anagram task (n = 15). Stress measures were taken again after the stressor and during recovery. The TSST significantly elevated systolic blood pressure, diastolic blood pressure, heart rate, and self-rated anxiety from pre-stress levels, replicating its stress-inducing properties. However, the ST and unsolvable anagrams only elevated heart rate, indicating that these methods are not as able to stimulate physiological or psychological stress. Overall, results indicate that out of these three laboratory stressors, the TSST clearly engages the stress response over the ST or unsolvable anagrams.


2018 ◽  
Vol 226 (3) ◽  
pp. 191-196 ◽  
Author(s):  
Annika Clamor ◽  
Katarina Krkovic

Abstract. Learning mechanisms may serve as a framework for understanding the formation of paranoia. Specifically, if paranoid thoughts after social stressors produce a short-term benefit for coping (e.g., downregulating arousal), the encountered negative reinforcement could lead to their excessive application and subsequently to long-term maladaptive convictions. The Trier Social Stress Test was utilized in healthy participants to examine this putative benefit. Participants rated paranoia at baseline and after the stressor. Subjective stress levels, negative affect, heart rate, and heart rate variability were assessed in the following rest phase (N = 59). Semipartial correlations showed that participants who responded with larger increases in paranoia were characterized by a lower heart rate in the subsequent rest phase. No associations were found with heart rate variability or psychological measures. Thus, paranoid thinking in healthy individuals could be an adaptive means for reestablishing some aspects of physiological homeostasis after a social stressor but further research is needed.


2020 ◽  
Vol 12 (11) ◽  
pp. 4497
Author(s):  
Kengo Mihara ◽  
Hisayoshi Okamura ◽  
Yoshihisa Shoji ◽  
Kyoko Tashiro ◽  
Yukie Kinoshita ◽  
...  

The current study aimed to examine the effects of personal growth (PG) on psychobiological responses at baseline and responsiveness to laboratory acute stress in students. Twenty-four healthy students were recruited as participants. Participants were screened from 203 candidates according to levels of PG using Ryff’s scale and classified into high and low PG groups. During the laboratory session, 13 high and 11 low PG participants underwent the Trier Social Stress Test. Heart rate and high-frequency (HF) heart rate variability were monitored throughout the experiment. Salivary free-3-methoxy-4-hydroxyphenylethyleneglycol (MHPG) and perceived stress were measured at baseline, immediately after tasks and after a recovery period. Baseline and recovery perceived stress (tense arousal) were significantly lower in the high PG group compared with the low PG group. Free-MHPG and HF component returned to baseline levels during recovery significantly more rapidly in the high PG group compared with the low PG group. There were no significant group differences in heart rate. The results showed that high PG students have lower noradrenaline and higher parasympathetic nervous system activity before and after acute stress. These findings suggest a protective psychobiological pathway linking PG with better psychosomatic health in students.


2019 ◽  
Vol 71 (1) ◽  
Author(s):  
Alireza Mohammadi ◽  
Asgar Emamgoli ◽  
Marjan Shirinkalam ◽  
Golam Hossein Meftahi ◽  
Keyvan Yagoobi ◽  
...  

Abstract Background As stress occurs repetitively every day, the biological modifiers should also have enough time to restore the normal state of hemostasis; otherwise, chronic stress would be anticipated. The aim of the present study was to examine the persistence of stress based on subjective emotion, salivary cortisol, and linear and non-linear features of heart rate variability (HRV) in both genders. Methods Thirty-three healthy young volunteers (23 men and 10 women) participating in this study were exposed to the Trier Social Stress Test (TSST). Moreover, the emotional visual analog scale (EVAS), salivary cortisol, and ECG recording in the rest state were taken before and after TSST as well as 20 min after recovery. Results According to the results of the two-way mixed model ANOVA, all volunteers showed a significant increase in EVAS after TSST which was restored to the baseline state after recovery. Notably, the women’s base of cortisol was significantly higher than men and the standard range of kit. Cortisol elevation was only observed in the men, and the significant increase of LF/HF ratio was observed in the women, while both did not retain to the baseline after recovery. The SD1 of Poincaré plot and spectral entropy decreased after stress in both genders. Moreover, there was a significant negative correlation between baseline level of cortisol and its elevation due to stress and some features of HRV. Conclusion The base of cortisol played a critical role in modifying the physiological response to stress. In addition, after recovery, no stressful emotion remained, while the non-linear features of HRV did not return to baseline.


Sign in / Sign up

Export Citation Format

Share Document