Application of Voice Analysis Programs to Quantify Fatigue
Department
Biological Sciences
Major
Chemistry
Research Advisor
Thimgan, Matthew S.
Advisor's Department
Biological Sciences
Funding Source
Missouri S&T OURE Program
Abstract
Fatigue can have disastrous consequences in surgery, transportation, and monitoring tasks. It would be useful to quantitatively identify the fatigue level of an employee to predict if they are at risk for a catastrophic error. Previous efforts to quantify include subjective measures, cognitive ability and motor skills. These metrics are currently inadequate to assess sleepiness in a real-world situation. We will investigate if quantifiable speech patterns correlate with fatigue. Quantitative information on how sleepy a person is could help determine how fit they are for activities. To test this hypothesis, subjects will record a test phrase in the morning and evening 2 times a week. Features of the voice will be quantified by voice analysis software and correlated with subjective sleepiness metrics, conventional cognitive and motor skills based fatigue tests. If a reliable correlation is found, a model will then be developed to predict fatigue using speech patterns.
Biography
Robert Block is a Junior studying Chemistry with an emphasis on Pre-Medicine and a minor in Biological Science. After graduating, he plans on attending medical school and becoming an anesthesiologist. His interests include robotics, martial arts, and video games.
Presentation Type
OURE Fellows Proposal Oral Applicant
Document Type
Presentation
Award
2016-2017 OURE Fellows recipient
Location
Turner Room
Presentation Date
11 Apr 2016, 1:00 pm - 1:20 pm
Application of Voice Analysis Programs to Quantify Fatigue
Turner Room
Fatigue can have disastrous consequences in surgery, transportation, and monitoring tasks. It would be useful to quantitatively identify the fatigue level of an employee to predict if they are at risk for a catastrophic error. Previous efforts to quantify include subjective measures, cognitive ability and motor skills. These metrics are currently inadequate to assess sleepiness in a real-world situation. We will investigate if quantifiable speech patterns correlate with fatigue. Quantitative information on how sleepy a person is could help determine how fit they are for activities. To test this hypothesis, subjects will record a test phrase in the morning and evening 2 times a week. Features of the voice will be quantified by voice analysis software and correlated with subjective sleepiness metrics, conventional cognitive and motor skills based fatigue tests. If a reliable correlation is found, a model will then be developed to predict fatigue using speech patterns.
