Audio Features Selection for Automatic Height Estimation from Speech

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6040)


Aiming at the automatic estimation of the height of a person from speech, we investigate the applicability of various subsets of speech features, which were formed on the basis of ranking the relevance and the individual quality of numerous audio features. Specifically, based on the relevance ranking of the large set of openSMILE audio descriptors, we performed selection of subsets with different sizes and evaluated them on the height estimation task. In brief, during the speech parameterization process, every input utterance is converted to a single feature vector, which consists of 6552 parameters. Next, a subset of this feature vector is fed to a support vector machine (SVM)-based regression model, which aims at the straight estimation of the height of an unknown speaker. The experimental evaluation performed on the TIMIT database demonstrated that: (i) the feature vector composed of the top-50 ranked parameters provides a good trade-off between computational demands and accuracy, and that (ii) the best accuracy, in terms of mean absolute error and root mean square error, is observed for the top-200 subset.


height estimation from speech speech parameterization feature ranking feature selection SVM regression models 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Fitch, W.T., Giedd, J.: Morphology and development of human vocal tract: a study using magnetic resonance imaging. Journal of Acoustical Society of America 106(3), 1511–1522 (1999)CrossRefGoogle Scholar
  2. 2.
    van Dommelen, W.A., Moxness, B.H.: Acoustic parameters in speaker height and weight identification: sex-specific behaviour. Language and Speech 38, 267–287 (1995)Google Scholar
  3. 3.
    van Oostendorp, M.: Schwa in phonological theory. GLOT International 3, 3–8 (1998)Google Scholar
  4. 4.
    Collins, S.A.: Men’s voices and women’s choices. Animal Behaviour 60, 773–780 (2000)CrossRefGoogle Scholar
  5. 5.
    Gonzalez, J.: Estimation of speaker’s weight and height from speech: a re-analysis of data from multiple studies by Lass and colleagues. Perceptual and Motor Skills 96, 297–304 (2003)CrossRefGoogle Scholar
  6. 6.
    Rendall, D., Kollias, S., Ney, C.: Pitch (F0) and formant profiles of human vowels and vowel-like baboon grunts: the role of vocalizer body size and voice-acoustic allometry. Journal of Acoustical Society of America 117(2), 1–12 (2005)CrossRefGoogle Scholar
  7. 7.
    Lass, N.J., Brown, W.S.: Correlation study of speaker’s heights, weights, body surface areas, and speaking fundamental frequencies. Journal of Acoustical Society of America 63(4), 700–703 (1978)CrossRefGoogle Scholar
  8. 8.
    Künzel, H.J.: How well does average fundamental frequency correlate with speaker height and weight? Phonetica 46, 117–125 (1989)CrossRefGoogle Scholar
  9. 9.
    Smith, D.R.R., Patterson, R.D., Turner, R., Kawahara, H., Irino, T.: The processing and perception of size information in speech sounds. Journal of Acoustical Society of America 117(1), 305–318 (2005)CrossRefGoogle Scholar
  10. 10.
    Dusan, S.: Estimation of speaker’s height and vocal tract length from speech signal. In: Proc. of the 9th European Conference on Speech Communication and Technology (Interspeech 2005), pp. 1989–1992 (2005)Google Scholar
  11. 11.
    Fant, G.: Acoustic Theory of Speech Production. Mouton, The Hague (1960)Google Scholar
  12. 12.
    Davis, S.B., Mermelstein, P.: Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Transactions on Acoustics, Speech and Signal Processing 28(4), 357–366 (1980)CrossRefGoogle Scholar
  13. 13.
    Eyben, F., Wöllmer, M., Schüller, B.: openEAR – introducing the Munich open-source emotion and affect recognition toolkit. In: Proc. 4th International HUMAINE Association Conference on Affective Computing and Intelligent Interaction 2009 (ACII 2009), September 10-12. IEEE, Amsterdam (2009)Google Scholar
  14. 14.
    Young, S., Evermann, G., Gales, M., Hain, T., Kershaw, D., Liu, X., Moore, G., Odell, J., Ollason, D., Povey, D., Valtchev, V., Woodland, P.: The HTK Book (for HTK Version 3.4). Cambridge University Engineering Department, Cambridge (2006)Google Scholar
  15. 15.
    Robnik-Šikonja, M., Kononenko, I.: An adaptation of Relief for attribute estimation in regression. In: Fourteenth International Conference on Machine Learning, pp. 296–304 (1997)Google Scholar
  16. 16.
    Scholkopf, B., Smola, A., Williamson, R., Bartlett, P.L.: New support vector algorithms. Neural Computation 12(5), 1207–1245 (2000)CrossRefGoogle Scholar
  17. 17.
    Garofolo, J.: Getting started with the DARPA-TIMIT CD-ROM: an acoustic phonetic continuous speech database. National Institute of Standards and Technology (NIST), Gaithersburgh, MD, USA (1988)Google Scholar
  18. 18.
    Pellom, B.L., Hansen, J.H.L.: Voice analysis in adverse conditions: the centennial Olympic park bombing 911 call. In: Proc. of the 40th Midwest Symposium on Circuits and Systems (MWSCAS 1997), vol. 2, pp. 873–876 (1997)Google Scholar
  19. 19.
    Witten, H.I., Frank, E.: Data Mining: Practical Machine Learning Tools and Techniques. Morgan Kaufmann Publishing, San Francisco (2005)zbMATHGoogle Scholar
  20. 20.
    Theodoridis, S., Koutroumbas, K.: Pattern Recognition, 4th edn. Academic Press, London (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  1. 1.Artificial Intelligence Group, Wire Communications Laboratory, Dept. of Electrical and Computer EngineeringUniversity of PatrasRion-PatrasGreece

Personalised recommendations