The Prediction of Fatigue Using Speech as a Biosignal

Baykaner, Khan; Huckvale, Mark; Whiteley, Iya; Ryumin, Oleg; Andreeva, Svetlana

doi:10.1007/978-3-319-25789-1_2

Cited by 3 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is in agreement with previous studies as these features have also been used in many speaker identification and verification approaches [8], [10], [29]. MFCC features, especially, have been applied to detect fatigue caused by sleep deprivation [30], [31]. Greeley et al used 36 MFCC features to detect fatigue from fixed words, comprised of 12 cepstral coefficients along with their first and second time derivatives [7].…”

Section: Is2011supporting

confidence: 80%

“…Greeley et al used 36 MFCC features to detect fatigue from fixed words, comprised of 12 cepstral coefficients along with their first and second time derivatives [7]. Baykaner et al used 19 MFCC features to detect fatigue from speech data from a book [31]. Given that the purpose of the study was to examine how 25-hour sleep deprivation affects speech recognition, it is not surprising that features including MFCC and other frequently chosen features from different times throughout the day resulted in higher performance than just using speech data from a particular time of the day or even a combination of two time sessions.…”

Section: Is2011mentioning

confidence: 99%

See 1 more Smart Citation

Machine-Learning-Based Closed-Set Text-Independent Speaker Identification Using Speech Recorded During 25 Hours of Prolonged Wakefulness

et al. 2021

View full text Add to dashboard Cite

We performed machine learning for text-independent speaker identification using speech recorded during the day, evening, and night, from subjects undergoing 25 hours of prolonged wakefulness. Subjects answered casual questions lasting approximately 3 minutes and described pictures presented to them for 0.5 minutes. We extracted 12,515 vocal features using OpenSmile software. For generalization of the training scheme, we segmented the 20 subjects into training and testing sets (10 subjects for each) and repeated testing four times with different subsets. Specifically, we used one set of 10 subjects to find the best feature-sets and the optimal machine-learning method, and the other set of 10 subjects was used to test the trained model. With trained machine-learning models using three speech sessions recorded throughout the day for speaker identification, we obtained 95% and 98.8% for balanced accuracies for daytime and evening speech, respectively, but 84.2% for nighttime-testing speech. With training data from all times of daydaytime, evening, and nighttime-we obtained 97.5%, 98.8%, and 98.1% for balanced accuracies for test data from daytime, evening, and nighttime speech, respectively; the overall accuracy was 98.1%. Prolonged wakefulness deteriorates the performance of machine-learning based speaker identification. This work suggests that machine-learning based speaker identification should be trained using speech data from both daytime and nighttime speech sessions for better overall accuracy. Machine learning can potentially be used for identifying a speaker's voice even when it is affected by tiredness and fatigue which are frequently encountered in scenarios such as the emergency rooms and long-duration repetitive task operations.

show abstract

Section: Is2011supporting

confidence: 80%

Section: Is2011mentioning

confidence: 99%

Machine-Learning-Based Closed-Set Text-Independent Speaker Identification Using Speech Recorded During 25 Hours of Prolonged Wakefulness

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In this section, models are trained to predict fatigue, on the assumption that latency and phase are the primary components of interest as suggested by Åkerstedt ( 2000 ) and Williamson et al ( 2011 ). Predictions of fatigue according to sleep latency on the same data set is presented in Baykaner et al ( 2015 ), where a binary classifier for fatigued/not-fatigued (based on sleep latency) achieved a classification accuracy of 80% for speaker independent features and 90% for speaker-dependent features. In contrast in this work, we train regression models for the continuous prediction of sleep latency and phase.…”

Section: Model Trainingmentioning

confidence: 93%

Predicting Fatigue and Psychophysiological Test Performance from Speech for Safety-Critical Environments

Baykaner

Huckvale

Whiteley

et al. 2015

Front. Bioeng. Biotechnol.

Self Cite

View full text Add to dashboard Cite

Automatic systems for estimating operator fatigue have application in safety-critical environments. A system which could estimate level of fatigue from speech would have application in domains where operators engage in regular verbal communication as part of their duties. Previous studies on the prediction of fatigue from speech have been limited because of their reliance on subjective ratings and because they lack comparison to other methods for assessing fatigue. In this paper, we present an analysis of voice recordings and psychophysiological test scores collected from seven aerospace personnel during a training task in which they remained awake for 60 h. We show that voice features and test scores are affected by both the total time spent awake and the time position within each subject’s circadian cycle. However, we show that time spent awake and time-of-day information are poor predictors of the test results, while voice features can give good predictions of the psychophysiological test scores and sleep latency. Mean absolute errors of prediction are possible within about 17.5% for sleep latency and 5–12% for test scores. We discuss the implications for the use of voice as a means to monitor the effects of fatigue on cognitive performance in practical applications.

show abstract