An Analysis of the Speech Under Stress Using the Two-Mass Vocal Fold Model

  • Xiao Yao
  • Takatoshi Jitsuhiro
  • Chiyomi Miyajima
  • Norihide Kitaoka
  • Kazuya Takeda
Conference paper

Abstract

We focus on the glottal source of speech production, which is essential for understanding the behavior of vocal fold when speech is produced under psychological stress. A spectral flatness measure (SFM) is introduced, as a useful tool, to evaluate stress levels in speech. Further, the relationship between the physical parameters of the two-mass vocal fold model and the proposed stress level measurement is established. The physical parameters of two-mass model are examined and analyzed comparing with measurements in order to estimate the state of vocal folds in people experiencing stress in the future. In this paper, experiments are performed using stressed speech gathered from real telephone conversations to evaluate the stress level measurement.Results show that the SFM can detect stress and can be used as a measurement for differentiating stressed from neutral speech. Furthermore, the changes in physical parameters can be analyzed to understand the behavior of vocal folds when stress occurs.

Keywords

Dition Tral 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Steeneken, H.J.M. and Hansen, J.H.L.: Speech Under Stress Conditions: Overview of the Effect on Speech Production and on System Performance. in Proc. ICASSP, 4, 2079–2082 (1999).Google Scholar
  2. 2.
    Cairns, D, Hansen, J.H.L.: Nonlinear Analysis and Detection of Speech Under Stressed Conditions. The Journal of the Acoustical Society of America, textbf96, 6, 3392–3400 (1994).Google Scholar
  3. 3.
    Junqua, J.C. : The Lombard reflex and its role on human listeners and automatic speech recognizers. J. Acoust. Soc. Amer., 1, 510–524, (1993).CrossRefGoogle Scholar
  4. 4.
    Bard, E. G., Sotillo, C., Anderson, A. H., Thompson, H. S., and Taylor, M. M.: The DCIEM map task corpus: Spontaneous dialogue under sleep deprivation and drug treatment, Speech Commun., 20, 71–84 (1996).CrossRefGoogle Scholar
  5. 5.
    Hansen, J. H. L.: Analysis and compensation of speech under stress and noise for environmental robustness in speech recognition, Speech Commun., 20, 151–173 (1996).CrossRefGoogle Scholar
  6. 6.
    Ishizaka, K., Flanagan, J.L.: Synthesis of voiced sounds from a two-mass model of the vocal cords, Bell.Syst.Tech.Journal, 51, 1233–1268 (1972).Google Scholar
  7. 7.
    Teffahi, H.: A two-mass model of the vocal folds: determination of control parameters. Multimedia computing and System (2009).Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2011

Authors and Affiliations

  • Xiao Yao
    • 1
  • Takatoshi Jitsuhiro
    • 2
  • Chiyomi Miyajima
    • 1
  • Norihide Kitaoka
    • 1
  • Kazuya Takeda
    • 1
  1. 1.Graduate School of Information ScienceNagoya UniversityAichiJapan
  2. 2.Department of Media InformaticsAichi University of TechnologyGamagoriJapan

Personalised recommendations