loading page

Controlling Speech Confounding in Psychophysiology Research: Speech detection via respiratory inductance plethysmography, thoracic impedance, accelerometers and gyroscopes
  • +1
  • Melisa Saygin,
  • Myrte Schoenmakers,
  • Martin Gevonden,
  • Eco de Geus
Melisa Saygin
VU Amsterdam

Corresponding Author:[email protected]

Author Profile
Myrte Schoenmakers
VU Amsterdam
Author Profile
Martin Gevonden
VU Amsterdam
Author Profile
Eco de Geus
VU Amsterdam
Author Profile

Abstract

Speech production interferes with accurate measurement of cardiac vagal activity during acute stress, attenuating the expected drop in heart rate variability in the respiratory frequency band. Speech also induces 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 is necessary to separate the physiological effects of psychosocial stress from those of speech. Using supervised machine learning (https://osf.io/bk9nf), we trained and tested speech classification models on data obtained from 56 participants (ages 18-39). 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 set 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 unbiased generalized performance estimates. Speech classification by the best model per method was then validated in the unseen 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 outperformed the other methods. These novel open-access models that leverage privacy-secure biosignals will enable researchers to detect speech and control for its confounding effects in ambulatory recordings, thereby enhancing the trustworthiness of psychophysiological findings.
Submitted to Psychophysiology
Assigned to Editor
Reviewer(s) Assigned
Submission Checks Completed
26 Jun 2024Review(s) Completed, Editorial Evaluation Pending
15 Jul 2024Reviewer(s) Assigned
13 Sep 2024Editorial Decision: Revise Minor