Human Voice as a Measure of Mental Load Level Purpose The aim of this study was to determine a reliable and efficient set of acoustic parameters of the human voice able to estimate individuals' mental load level. Implementing detection methods and real-time analysis of mental load is a major challenge for monitoring and enhancing human task performance, especially during ... Research Article
Research Article  |   November 08, 2018
Human Voice as a Measure of Mental Load Level
 
Author Affiliations & Notes
  • Stanislas Boyer
    Cognition, Languages, Language, Ergonomics–Work & Cognition Laboratory (CLLE-LTC), University of Toulouse and Centre National de la Recherche Scientifique, France
  • Pierre-Vincent Paubel
    Cognition, Languages, Language, Ergonomics–Work & Cognition Laboratory (CLLE-LTC), University of Toulouse and Centre National de la Recherche Scientifique, France
  • Robert Ruiz
    Audiovisual Research Laboratory (LARA), University of Toulouse, France
  • Radouane El Yagoubi
    Cognition, Languages, Language, Ergonomics–Work & Cognition Laboratory (CLLE-LTC), University of Toulouse and Centre National de la Recherche Scientifique, France
  • Agnès Daurat
    Cognition, Languages, Language, Ergonomics–Work & Cognition Laboratory (CLLE-LTC), University of Toulouse and Centre National de la Recherche Scientifique, France
  • Disclosure: The authors have declared that no competing interests existed at the time of publication.
    Disclosure: The authors have declared that no competing interests existed at the time of publication. ×
  • Correspondence to Robert Ruiz: robert.ruiz@univ-tlse2.fr
  • Editor-in-Chief: Julie Liss
    Editor-in-Chief: Julie Liss×
  • Editor: Michelle Ciucci
    Editor: Michelle Ciucci×
Article Information
Hearing & Speech Perception / Acoustics / Attention, Memory & Executive Functions / Speech, Voice & Prosody / Speech / Research Articles
Research Article   |   November 08, 2018
Human Voice as a Measure of Mental Load Level
Journal of Speech, Language, and Hearing Research, November 2018, Vol. 61, 2722-2734. doi:10.1044/2018_JSLHR-S-18-0066
History: Received February 22, 2018 , Revised April 10, 2018 , Accepted June 7, 2018
 
Journal of Speech, Language, and Hearing Research, November 2018, Vol. 61, 2722-2734. doi:10.1044/2018_JSLHR-S-18-0066
History: Received February 22, 2018; Revised April 10, 2018; Accepted June 7, 2018

Purpose The aim of this study was to determine a reliable and efficient set of acoustic parameters of the human voice able to estimate individuals' mental load level. Implementing detection methods and real-time analysis of mental load is a major challenge for monitoring and enhancing human task performance, especially during high-risk activities (e.g., flying aircraft).

Method The voices of 32 participants were recorded during a cognitive task featuring word list recall. The difficulty of the task was manipulated by varying the number of words in each list (i.e., between 1 and 7, corresponding to 7 mental load conditions). Evoked pupillary response, known to be a useful proxy of mental load, was recorded simultaneously with speech to attest variations in mental load level during the experimental task.

Results Classic features (fundamental frequency, its standard deviation, number of periods) and original features (frequency modulation and short-term variation in digital amplitude length) of the acoustic signals were predictive of memory load condition. They varied significantly according to the number of words to recall, specifically beyond a threshold of 3–5 words to recall, that is, when memory performance started to decline.

Conclusions Some acoustic parameters of the human voice could be an appropriate and efficient means for detecting mental load levels.

Order a Subscription
Pay Per View
Entire Journal of Speech, Language, and Hearing Research content & archive
24-hour access
This Article
24-hour access