Analysis of Natural Speech under Stress

• Authors: G. Demenko , M. Jastrzębska
• Languages of publication: EN

Abstracts

EN

This paper presents how voice stress is manifested in the acoustic and phonetic structure of the speech signal. Out of 60000 authentic Police 997 emergency phone calls, 22000 were automatically selected, a few hundred of which were chosen for acoustic evaluation, the basis for selection being a perceptual assessment. In highly stressful conditions (e.g. panic) a systematic dynamic over-one-octave shift in pitch and significant increase in speech tempo was observed. In states of depression a systematic down shift in pitch and significant decrease in speech tempo was observed. Basic statistical measurements for stressed and neutral speech run over the database showed the relevance of the arousal and potency dimension in stress processing. In speech produced under fear an upward shift in pitch register was significant (in comparison to neutral speech), while speech recorded during experiencing anger was characterized by an increase in F_0 range.

Keywords

EN

43.72.-p; 43.72.Uv

• Publisher: Institute of Physics, Polish Academy of Sciences
• Journal: Acta Physica Polonica A
• Year: 2012
• Volume: 121
• Issue: 1A
• Pages: A-92-A-95

Dates

published

2012-01

Contributors

author

G. Demenko

• Poznań Supercomputing and Networking Center, Zwierzyniecka 20, 60-814 Poznań, Poland
• Uniwersytet im. Adama Mickiewicza w Poznaniu, H. Wieniawskiego 1, 61-712 Poznań, Poland

author

M. Jastrzębska

• Uniwersytet im. Adama Mickiewicza w Poznaniu, H. Wieniawskiego 1, 61-712 Poznań, Poland

References

• [1] G. Demenko, in: Proc. Speech Prosody Conf. 2008, Campinas (Brasil), Eds. P.A. Barbosa, S. Madureira, C. Reis, ISCA Archive, 2008, p. 53
• [2] L. Vidrascu, L. Devillers, in: Proc. Interspeech,2005, p. 1841
• [3] R. Cowie, R.R. Cornelius, Speech Commun. 40, 5 (2003)
• [4] K. Alter, E. Rank, S.A. Kotz, U. Toepel, M. Besson, A. Schirmer, A.D. Friederici, Speech Commun. 40, 61 (2003)
• [5] P.-Y. Oudeyer, Int. J. of Human-Computer Studies 59, 157 (2003)
• [6] J. Hansen, C. Swail, A. South, R. Moore, H. Steeneken, E.J. Cupples, T. Anderson, C. Vloeberghs, I. Trancoso, P. Verlinde, Nato report (2007), http://www-gth.die.upm.es/research/documentation/referencias/Hansen_TheImpact.pdf
• [7] R. Huber, A. Batliner, J. Buckow, E. Noth, V. Warnke, H. Niemann, in: Proc. Int. Conf. on Spoken Language Processing, Beijing (China), ISCA Archive, 2000, p. 665
• [8] K.R. Scherer, Soc. Sci. Inform. 44, 695 (2005)
• [9] A. Batliner, K. Fischer, R. Huber, J. Spilker, E. Noth, in: Speech Emotion-2000, ISCA Archive, 2000, p. 195
• [10] P. Ekman, Cognition Emotion 6, 169 (1992)
• [11] R.J. Fontaine, K.R. Scherer, E.B. Roesch, P.C. Ellsworth, Psychol. Sci. 18, 1050 (2007)
• [12] D. Deliyski, in: Proc. Eurospeech'93, ISCA Archive, 1993, p. 1969
• [13] A. Protopapas, P. Lieberman, J. Acoust. Soc. Am. 101, 2268 (1997)

Identifiers

DOI

10.12693/APhysPolA.121.A-92