Field Study Evaluation of Cepstrum Coefficient Speech Analysis for Fatigue in Aviation Cabin Crew
Year: 2013
Type: article
Abstract: Impaired neurobehavioral performance induced by fatigue may compromise safety in 24-hr operational \nenvironmentssuch as aviation. As such, non-invasive, reliable, and valid methods of objectively detecting \ncompromised performance capacity in operational settings could be valuable as a means of identifying, \npreventing, and mitigating fatigue-induced safety risks. One approach that has attracted attention in recent \nyears is quantitative speech analysis, but the extent of its operational feasibility, validity of the metrics, and \nsensitivity to operationally-relevant factors in aviation remains unknown. To this end, the present report offers \nan initial proof-of-concept evaluation of a speech analysis method based on Cepstrum Coefficient modeling,\nusing voice files from a broad sample of 195 cabin crew personnel collected during the 2009-2010 U.S. Civil \nAerospace Medical Institute-sponsored Flight Attendant Field Study (Roma et al., 2010).\nUsing a personal digital assistant device, participants recited five standardized phrases in random order \nbefore and after each workday and sleep episode throughout their respective 3-4 week study periods.\nOperational acceptability of the procedure was high, as indicated by high protocol compliance and, despite the \ninherent variability of the timing and environments in which the test sessions occurred, the 13,975 files from \n2,795 valid sessions were of sufficient quality for formal analysis. Individualized “baseline” speech models \nwere built from the files collected during test sessions coinciding with optimal neurobehavioral performance, \nas determined by 5-min Psychomotor Vigilance Test (PVT) reaction times(RT), then speech deviation scores \nrelative to individual baseline models were calculated for the test sessions that preceded and concluded each \n“trip” of multiple consecutive work days. Regarding validity, speech scores correlated significantly with PVT \nRTs and Lapses(RTs 500 msec), with a stronger relationship to Lapses, but high variability at the low range \nof both performance variables suggests the influence of other factors. Regarding sensitivity to operational \nfactors, average Pre-Trip vs. Post-Trip speech scores differed significantly, although scores unexpectedly \ndecreased from Pre to Post, an artifact attributable to the composition of the baseline session pool.\nNonetheless, the pattern of speech data echoed performance data from our previous report in which scores \nwere most affected in crew of Regional carriers, with Junior seniority, and in Domestic operations.\nThese initial results reveal promising validity and sensitivity of Cepstrum Coefficient modeling for speech \nsignal analysis of fatigue in dynamic operational environments. Remaining questions underscore the need to \nfurther explore the dataset to determine the precise relationship between speech production and \nneurobehavioral performance capacity, the parameters for constructing individualized models, and \nstandardized quantitative speech-based definitions of fatigue.\n
Source: ROSA P
Language: English
Subfield: Experimental and Cognitive Psychology
Field: Psychology
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W305338691