Large Sleepy Reading Corpus (LSRC): Applying Read Speech for Detecting Sleepiness

Konferenz: Speech Communication - 12. ITG-Fachtagung Sprachkommunikation
05.10.2016 - 07.10.2016 in Paderborn, Deutschland

Tagungsband: ITG-Fb. 267: Speech Communication

Seiten: 4Sprache: EnglischTyp: PDF

Persönliche VDE-Mitglieder erhalten auf diesen Artikel 10% Rabatt

Autoren:
Krajewski, Jarek (Institute of Safety Technology, University of Wuppertal, 42119 Wuppertal, Germany & Engineering Psychology, Rhenish University of Applied Science Cologne, 50825 Köln, Germany)
Schnieder, Sebastian (Business Psychology, University of Applied Science for Media, Communication and Business, 13355 Berlin, Germany)
Monschau, Christopher (Engineering Psychology, Rhenish University of Applied Science Cologne, 50825 Köln, Germany)
Titt, Raphael (Social Psychology, University of Tuebingen, 72074 Tübingen, Germany)
Sommer, David; Golz, Martin (Applied Computational Intelligence, University of Applied Sciences Schmalkalden, 98574 Schmalkalden, Germany)

Inhalt:
This paper describes a Large Sleepy Reading Corpus (LSRC) based on sleep deprivation data (N=402; total duration 22 h). During the sleep deprivation, a standardized self-report scale was used just before the recordings to determine the sleepiness state. The speech material consisted of different reading passages. In order to investigate sleepiness induced speech changes, a standard set of spectral and prosodic features was extracted from recordings. After applying a standard openSMILE feature set, and a SVM regression we achieved correlation coefficients of .44 for male and .53 for female speaker.