This paper describes a promising sleepiness detection approach based on prosodic and spectral speech characteristics and illustrates the validity of this method by briefly discussing results from a sleep deprivation study (N=20). We conducted a within-subject sleep deprivation design (8.00 p.m. to 4.00 a.m.). During the night of sleep deprivation, a standardized self-report scale was used every hour just before the recordings to determine the sleepiness state. The speech material consisted of simulated driver assistance system phrases. In order to investigate sleepiness induced speech changes, a standard set of spectral and prosodic features were extracted from the sentences. After forward selection and a PCA were employed on the feature space in an attempt to prune redundant dimensions, LDA- and ANN-based classification models were trained. The best level-0 model (RA15, LDA) offers a mean accuracy rate of 80.0% for the two-class problem. Using an ensemble classification strategy (majority voting as meta-classifier) we achieved a accuracy rate of 88.2%.
Bibliographic reference. Krajewski, Jarek / Kröger, Bernd (2007): "Using prosodic and spectral characteristics for sleepiness detection", In INTERSPEECH-2007, 1841-1844.