Speaker
Description
This study consists of two components: a systematic review and a protocol validation. The first part aims to synthesize existing evidence on how workload, stress, fatigue, and sleepiness affect speech, with a focus on identifying vocal markers of these states in aviation contexts. Following PRISMA guidelines, a comprehensive search was conducted across Scopus, ScienceDirect, PsycINFO, and Web of Science. Twenty studies met the inclusion criteria and were analyzed to extract recurring vocal features associated with pilots’ and air traffic controllers’(ATCs) psychophysiological states. Results indicate that stress and high workload are consistently linked to increased pitch and vocal intensity, reflecting sympathetic nervous system activation. In contrast, fatigue and sleepiness are associated with reduced vocal energy, slower speech rate, and more frequent pauses, suggesting central nervous system downregulation. Mel-frequency cepstral coefficients (MFCCs) emerged as robust and reliable markers across conditions.
Building on these findings, the second part of the study focused specifically on stress, validating an acoustic analysis protocol using real-world pilot-ATC communications recorded during both routine operations and high-stress emergencies. Vocal features were extracted using Praat and standardized via z-scores to control for inter-speaker variability. Confidence intervals were calculated separately for routine and emergency phases to assess changes in vocal behavior with greater precision.
The integration of this validated protocol into aviation safety systems offers promising opportunities for real-time vocal monitoring, enabling early detection of stress and timely interventions—ultimately enhancing performance and reducing risk in critical aviation tasks.
| If you're submitting a symposium, or a talk that is part of a symposium, is this a junior symposium? | No |
|---|
