International Conference on Statistical Language and Speech Processing

Statistical Language and Speech Processing pp 8-17

The Prediction of Fatigue Using Speech as a Biosignal

  • Khan Baykaner
  • Mark Huckvale
  • Iya Whiteley
  • Oleg Ryumin
  • Svetlana Andreeva
Conference paper

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

Part of the Lecture Notes in Computer Science book series (LNCS, volume 9449)
Cite this paper as:
Baykaner K., Huckvale M., Whiteley I., Ryumin O., Andreeva S. (2015) The Prediction of Fatigue Using Speech as a Biosignal. In: Dediu AH., Martín-Vide C., Vicsi K. (eds) Statistical Language and Speech Processing. Lecture Notes in Computer Science, vol 9449. Springer, Cham

Abstract

Automatic systems for estimating operator fatigue have application in safety-critical environments. We develop and evaluate a system to detect fatigue from speech recordings collected from speakers kept awake over a 60-hour period. A binary classification system (fatigued/not-fatigued) based on time spent awake showed good discrimination, with 80 % unweighted accuracy using raw features, and 90 % with speaker-normalized features. We describe the data collection, feature analysis, machine learning and cross-validation used in the study. Results are promising for real-world applications in domains such as aerospace, transportation and mining where operators are in regular verbal communication as part of their normal working activities.

Keywords

Fatigue Speech Computational paralinguistics 

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Khan Baykaner
    • 1
  • Mark Huckvale
    • 1
  • Iya Whiteley
    • 2
  • Oleg Ryumin
    • 3
  • Svetlana Andreeva
    • 3
  1. 1.Speech Hearing and Phonetic Sciences, UCLLondonUK
  2. 2.Centre for Space Medicine, UCLDorkingUK
  3. 3.Gagarin Cosmonaut Training CentreStar CityRussia

Personalised recommendations