Department of Head and Skin, Department of Psychiatry and Medical Psychology, , Ghent University, University Hospital Ghent (UZ Ghent), Corneel Heymanslaan 10-13K12, 9000, Ghent, Belgium.
Ghent Experimental Psychiatry (GHEP) Lab, Ghent University, Ghent, Belgium.
Behav Res Methods. 2022 Apr;54(2):910-921. doi: 10.3758/s13428-021-01670-x. Epub 2021 Aug 6.
Recently, the possibilities of detecting psychosocial stress from speech have been discussed. Yet, there are mixed effects and a current lack of clarity in relations and directions for parameters derived from stressed speech. The aim of the current study is - in a controlled psychosocial stress induction experiment - to apply network modeling to (1) look into the unique associations between specific speech parameters, comparing speech networks containing fundamental frequency (F0), jitter, mean voiced segment length, and Harmonics-to-Noise Ratio (HNR) pre- and post-stress induction, and (2) examine how changes pre- versus post-stress induction (i.e., change network) in each of the parameters are related to changes in self-reported negative affect. Results show that the network of speech parameters is similar after versus before the stress induction, with a central role of HNR, which shows that the complex interplay and unique associations between each of the used speech parameters is not impacted by psychosocial stress (aim 1). Moreover, we found a change network (consisting of pre-post stress difference values) with changes in jitter being positively related to changes in self-reported negative affect (aim 2). These findings illustrate - for the first time in a well-controlled but ecologically valid setting - the complex relations between different speech parameters in the context of psychosocial stress. Longitudinal and experimental studies are required to further investigate these relationships and to test whether the identified paths in the networks are indicative of causal relationships.
最近，人们探讨了从言语中检测心理社会压力的可能性。然而，目前对于应激言语中得出的参数之间的关系和方向仍存在不一致，且缺乏明确性。本研究的目的是——在一个受控的心理社会应激诱导实验中——应用网络模型来：(1) 探究特定言语参数之间的独特关联，比较在应激诱导前后包含基频（F0）、抖动、平均浊音段长度和谐噪比（HNR）的言语网络，以及 (2) 检查每个参数在应激诱导前后的变化（即变化网络）与自我报告的负性情绪变化之间的关系。结果表明，在应激诱导前后，言语参数的网络是相似的，其中 HNR 起着核心作用，这表明复杂的相互作用和每个使用的言语参数之间的独特关联不受心理社会应激的影响（目标 1）。此外，我们发现了一个变化网络（由应激前后的差值组成），其中抖动的变化与自我报告的负性情绪变化呈正相关（目标 2）。这些发现首次在一个控制良好但生态有效的环境中说明了心理社会应激背景下不同言语参数之间的复杂关系。需要进行纵向和实验研究来进一步调查这些关系，并测试网络中确定的路径是否指示因果关系。
