Vocal Instability as a Sensitive Biomarker for Driving Stress: Decoupling Cognitive Load and Environmental Friction in a Real-World Dual-Task Protocol

Year 2026, Volume: 15 Issue: 1 , 448 - 464 , 24.03.2026

Dağhan Doğan

https://doi.org/10.17798/bitlisfen.1833468

https://izlik.org/JA24MW47SZ

Abstract

Driver stress and cognitive workload are regarded as critical safety determinants within modern transportation systems. Although vocal acoustic analysis is considered a promising, non-invasive monitoring technique, the existing literature has been observed to generally lack ecological validity, and difficulties have been experienced in causally attributing the source of stress—whether it is internal cognitive load (CL) from secondary tasks or external environmental friction (EF) from traffic.
To address this gap, a single-subject (N=1) case study design was utilized within a real-world dual-task protocol. Within this protocol, a driver was required to maintain continuous conversation while navigating two distinct environments: a high-friction urban congestion segment (short route) and a hybrid urban and intercity segment (long route). A custom weighted acoustic stress index and the instantaneous pitch standard deviation (vocal instability) were analyzed.
The findings demonstrate that the constant demand of the dual-task establishes a dominant, consistent moderate stress baseline (approx. 34–36%) that is decoupled from routine traffic fluctuations and congestion level differences. Although the average stress level was maintained consistently, pitch standard deviation was proven to be a more sensitive metric: this metric was found to be significantly lower on the long route (hybrid segment) when compared to the short route (pure urban congestion). With this finding, the ability of vocal instability to effectively decouple the contributions of CL and EF is confirmed; thus, empirical evidence is provided that a stabilizing effect on the voice is created by low-demand highway segments, even if the overall vocal load remains moderate. Through this research, vocal instability is validated as a valuable, sensitive biomarker that is necessary for the development of context-aware in-vehicle systems capable of accurately distinguishing between distraction-related stress and environmental stress.

Keywords

Driving stress , Cognitive load , Vocal biomarkers , Pitch variability , Vocal instability , Dual-task protocol

Ethical Statement

The study is complied with research and publication ethics.

References

• G. Matthews, P. A. Desmond, and K. Gilliland, “The stress of driving: A diary study,” J. Appl. Psychol., vol. 84, no. 4, pp. 613–620, 1999.
• S. Nandan, S. Mandal, and P. Ghosal. "Stress Detection and Monitoring: A Systematic Review." 2024 IEEE International Symposium on Smart Electronic Systems (ISES). IEEE, 2024, pp. 309-314.
• J. A. Healey and R. W. Picard, “Detecting stress during real-world driving tasks using physiological sensors,” IEEE Trans. Intell. Transp. Syst., vol. 6, no. 2, pp. 156–166, 2005.
• P. R. Anciaes, “Effects of the roadside visual environment on driver wellbeing and behaviour–a systematic review,” Transp. Rev., vol. 43, no. 4, pp. 571–598, 2023.
• M. A. Recarte and L. M. Nunes, “Mental workload while driving: Effects on visual search, discrimination, and decision making,” J. Exp. Psychol. Appl., vol. 9, no. 2, pp. 119–133, 2003.
• J. Engström, E. Johansson, and J. Östlund, “Effects of visual and cognitive load in real and simulated motorway driving,” Transp. Res. Part F Traffic Psychol. Behav., vol. 8, no. 2, pp. 97–120, 2005.
• J. Lee, H. Lee, and M. Shin, “Driving stress detection using multimodal convolutional neural networks with nonlinear representation of short-term physiological signals,” Sensors, vol. 21, no. 7, p. 2381, 2021.
• H. Boril, P. Boyraz, and J. H. L. Hansen, “Towards multi-modal driver's stress detection,” in Proc. 10th Annu. Conf. Int. Speech Commun. Assoc. (INTERSPEECH 2009), Brighton, UK, 2009, pp. 1843–1846.
• C. D. Katsis, N. Katertsidis, G. Ganiatsas, and D. I. Fotiadis, “Toward emotion recognition in car-racing drivers: A biosignal processing approach,” IEEE Trans. Syst., Man, Cybern. A Syst. Humans, vol. 38, no. 3, pp. 502–512, 2008.
• G. Taskasaplidis, D. A. Fotiadis and P. D. Bamidis, "Review of Stress Detection Methods Using Wearable Sensors," in IEEE Access, vol. 12, pp. 38219-38246, 2024,
• G. Giannakakis, et al. "Review on psychological stress detection using biosignals." IEEE transactions on affective computing, vol. 13, no. 1, pp. 440-460, 2019.
• K. R. Scherer, et al. "Acoustic correlates of task load and stress." Interspeech. 2002.
• D. D. L. Veiga, et al. "The Fundamental Frequency of Voice as a Potential Stress Biomarker: A Systematic Review and Meta–Analysis." Stress and Health, vol. 41, no. 5, e70112, 2025.
• M. Van Puyvelde, et al. "Voice stress analysis: A new framework for voice and effort in human performance." Frontiers in psychology, vol. 9, no. 1994, 2018.
• B. Schuller, B. Vlasenko, F. Eyben, G. Rigoll, and A. Wendemuth, “Acoustic emotion recognition: A benchmark comparison of performances,” in 2009 IEEE Workshop Autom. Speech Recognit. Understanding, pp. 552–557, 2009.
• F. Eyben et al. “The Geneva Minimalistic Acoustic Parameter Set (GeMAPS) for voice research and affective computing,” IEEE Trans. Affect. Comput., vol. 7, no. 2, pp. 190–202, 2015.
• H. Boril, P. Boyraz, and J. H. L. Hansen, “Analysis and detection of cognitive load and frustration in drivers’ speech,” EURASIP J. Audio, Speech, Music Process., vol. 2011, no. 1, p. 6, 2011.
• P. Lu, L. Tsao, and L. Ma, "Daily stress detection from real-life speeches using acoustic and semantic information." Ergonomics, vol. 68, no. 10, pp. 1694-1717, 2025.
• L. Beckes and J. A. Coan, “Social baseline theory: The role of social proximity in emotion and economy of action,” Soc. Personal. Psychol. Compass, vol. 5, no. 12, pp. 976–988, 2011.
• Y. Dong, Z. Hu, K. Uchimura, and N. Murayama, “Driver inattention monitoring system for intelligent vehicles: A review,” IEEE Trans. Intell. Transp. Syst., vol. 12, no. 2, pp. 596–614, 2011.
• T. F. Quatieri, S. N. Orozco, & D. Plotkin, “Vocal biomarkers to discriminate cognitive load in a working memory task”. In Proceedings of Interspeech, pp. 1105-1109, Dresden, Germany, 2015.