Ambulatory wearable monitoring of human physiology is increasingly utilized in the fields of psychology, movement sciences, and medicine. With the rapid growth of available consumer- and research-oriented wearables, researchers are faced with a multitude of devices to choose from. It is unfeasible timewise for researchers to determine all relevant technical specifications, available signals, signal sampling details, and (raw) data availability, and conduct a search of studies regarding the reliability, validity, and usability of wearables. Thus, selection of wearables for a given study proves highly challenging and will often be unsystematic and uninformed. The 10-year research program Stress in Action initiated a publicly accessible database of wearable ambulatory monitoring devices. We outline the genesis and final structure of the first version of the Stress in Action Wearables Database (SiA-WD) and a summary of the characteristics of the wearables it currently contains. Furthermore, one short-term (2 days) and one long-term (3 months) scenario from the field of stress research are provided with walkthroughs of how the SiA-WD can help select the optimal wearable for a specific research project. Insights gathered include the scarceness of studies testing wearable user-friendliness, inconsistencies in reported validity statistics, and imprecise manufacturer documentation on recorded physiological data such as sampling rate (or window) of signals and parameter extraction. The SiA-WD is the first open-access database to simultaneously include physiological sampling information and technical specifications along with a systematic reliability, validity, and usability search. It will be iteratively expanded to facilitate informed and time-efficient wearable selection. For access to the database, see the following: https://osf.io/umgvp/.

Speech production interferes with the measurement of changes in cardiac vagal activity during acute stress by attenuating the expected drop in heart rate variability. Speech also induces cardiac sympathetic changes similar to those induced by psychological stress. In the laboratory, confounding of physiological stress reactivity by speech may be controlled experimentally. In ambulatory assessments, however, detection of speech episodes would be necessary to separate the physiological effects of psychosocial stress from those of speech. Using machine learning (https://osf.io/bk9nf), we trained and tested speech classification models on data from 56 participants (ages 18–39) under controlled laboratory conditions. They were equipped with privacy-secure wearables measuring thoracoabdominal respiratory inductance plethysmography (RIP from a single and a dual-band set-up), thoracic impedance pneumography, and an upper sternum positioned unit with triaxial accelerometers and gyroscopes. Following an 80/20 train-test split, nested cross-validations were run with the machine learning algorithms XGBoost, gradient boosting, random forest, and logistic regression on the training set to get generalized performance estimates. Speech classification by the best model per method was then validated in the test set. Speech versus no-speech classification performance (AUC) for both nested cross-validation and test set predictions was excellent for thorax–abdomen RIP (nested cross-validation: 96.6%, test set prediction: 98.5%), thorax-only RIP (97.5%, 99.1%), impedance (97.0%, 97.8%), and accelerometry (99.3%, 99.6%). The sternal accelerometer method outperformed others. These open-access models leveraging biosignals have the potential to also work in daily life settings. This could enhance the trustworthiness of ambulatory psychophysiology, by enabling detection of speech and controlling for its confounding effects on physiology.