Advertisement

Evaluation of Speech Emotion Classification Based on GMM and Data Fusion

  • Martin Vondra
  • Robert Vích
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5641)

Abstract

This paper describes continuation of our research on automatic emotion recognition from speech based on Gaussian Mixture Models (GMM). We use similar technique for emotion recognition as for speaker recognition. From previous research it seems to be better to use a lesser number of GMM components than is used for speaker recognition and better results are also achieved for a greater number of speech parameters used for GMM modeling. In previous experiments we used suprasegmental and segmental parameters separately and also together, which can be described as fusion on feature level. The experiment described in this paper is based on an evaluation of score level fusion for two GMM classifiers used separately for segmental and suprasegmental parameters. We evaluate two techniques of score level fusion – dot product of scores from both classifiers and maximum selection and maximum confidence selections.

Keywords

Gaussian Mixture Model Emotion Recognition Speaker Recognition Level Fusion Recognition Score 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Dellaert, F., Polzin, T., Waibel, A.: Recognizing Emotion in Speech. In: The Fourth International Conference on Spoken Language Processing ICSLP 1996, Philadelphia, pp. 1970–1973 (1996)Google Scholar
  2. 2.
    Morrison, D., Wang, R., De Silva, L.C.: Ensemble methods for spoken emotion recognition in call-centers. Speech Communication 49, 98–112 (2007)CrossRefGoogle Scholar
  3. 3.
    Truong, K.P., Leeuven, D.A.: An ‘open-set’ detection evaluation methology for automatic emotion recognition in speech. In: ParaLing 2007: Workshop on Paralinguistic Speech - between models and data, Saarbrücken, Germany (2007)Google Scholar
  4. 4.
    Nwe, T.L., Foo, S.W., DeSilva, L.C.: Speech emotion recognition using hidden Markov models. Speech Communication 41, 603–623 (2003)CrossRefGoogle Scholar
  5. 5.
    Vondra, M., Vích, R.: Recognition of Emotions in German Speech using Gaussian Mixture Models. In: Esposito, A., Hussain, A., Marinaro, M., Martone, R. (eds.) Multimodal Signals 2008. LNCS, vol. 5398, pp. 256–263. Springer, Heidelberg (2008)Google Scholar
  6. 6.
    Vondra, M., Vích, R.: Evaluation of Automatic Speech Emotion Recognition Based on Gaussian Mixture Models. In: Proc. 19. Konferenz Elektronische Sprachsignalverarbeitung, Frankfurt am Main, September 8-10, pp. 172–176 (2008)Google Scholar
  7. 7.
    Vích, R., Vondra, M.: Experimente mit dem Teager Energie Operator. In: Proc. 19. Konferenz Elektronische Sprachsignalverarbeitung, Frankfurt am Main, September 8-10, pp. 29–36 (2008)Google Scholar
  8. 8.
    Burkhardt, F., Paeschke, A., Rolfes, M., Sendlmeier, W., Weiss, B.: A Database of German Emotional Speech. In: Proc. Interspeech 2005, Lisbon, Portugal, September 4-8 (2005)Google Scholar
  9. 9.
    Sjölander, K., Beskow, J.: Wavesurfer, http://www.speech.kth.se/wavesurfer/
  10. 10.
    Brookes, M.: VOICEBOX: Speech Processing Toolbox for MATLAB, http://www.ee.ic.ac.uk/hp/staff/dmb/voicebox/voicebox.html
  11. 11.
    Reynolds, D.A.: Speaker identification and verification using Gaussian mixture speaker models. Speech Communication 17, 91–108 (1995)CrossRefGoogle Scholar
  12. 12.
    Kinnunen, T., Hautamäki, V., Fränti, P.: On the fusion of dissimilarity- based classifiers for speaker identification. In: Proc. 8th European Conference on Speech Communication and Technology (Eurospeech 2003), Geneva, Switzerland, pp. 2641–2644 (2003)Google Scholar
  13. 13.
    Shami, M., Verhelst, W.: An evaluation of the robustness of existing supervised machine learning approaches to the classification of emotions in speech. Speech Communication 49, 201–212 (2007)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Martin Vondra
    • 1
  • Robert Vích
    • 1
  1. 1.Institute of Photonics and ElectronicsAcademy of Sciences of the Czech RepublicPrague 8Czech Republic

Personalised recommendations