A Bayesian Approach to Emotion Detection in Dialogist’s Voice for Human Robot Interaction

  • Shohei Kato
  • Yoshiki Sugino
  • Hidenori Itoh
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4252)


This paper proposes a method for sensitivity communication robots which infer their dialogist’s emotion. The method is based on the Bayesian approach: by using a Bayesian modeling for prosodic features. In this research, we focus the elements of emotion included in dialogist’s voice. Thus, as training datasets for learning Bayesian networks, we extract prosodic feature quantities from emotionally expressive voice data. Our method learns the dependence and its strength between dialogist’s utterance and his emotion, by building Bayesian networks. Bayesian information criterion, one of the information theoretical model selection method, is used in the building Bayesian networks. The paper finally proposes a reasoner to infer dialogist’s emotion by using a Bayesian network for prosodic features of the dialogist’s voice. The paper also reports some empirical reasoning performance.


Bayesian Network Bayesian Approach Emotion Recognition Emotional Content Emotional Facial Expression 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Akiba, T., Tanaka, H.: A Bayesian approach for user modelling in dialog systems. In: 15th International Conference of Computational Linguistics, pp. 1212–1218 (1994)Google Scholar
  2. 2.
    Cooper, G.F., Herskovits, E.: A Bayesian method for constructing Bayesian belief networks from databases, pp. 86–94 (1991)Google Scholar
  3. 3.
    Cooper, G.F., Herskovits, E.: A Bayesian method for the induction of probabilistic networks from data. Machine Learning 9, 309–347 (1992)MATHGoogle Scholar
  4. 4.
    Cowie, R., Douglas-Cowie, E., Tsapatsoulis, N., Votsis, G., Kollias, S., Fellenz, W., Taylor, J.G.: Emotion recognition in human-computer interaction. IEEE Signal Processing Magazine 18(1), 32–80 (2001)CrossRefGoogle Scholar
  5. 5.
    Dempster, A., Laird, N., Rubin, D.: Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royals Statistical Society B 39, 1–38 (1977)MathSciNetGoogle Scholar
  6. 6.
    Endo, G., Nakanishi, J., Morimoto, J., Cheng, G.: Experimental studies of a neural oscillator for biped locomotion with QRIO. In: IEEE International Conference on Robotics and Automation (ICRA 2005), pp. 598–604 (2005)Google Scholar
  7. 7.
    Fujita, M.: Development of an Autonomous Quadruped Robot for Robot Entertainment. Autonomous Robots 5, 7–18 (1998)CrossRefGoogle Scholar
  8. 8.
    Fujita, M., Kitano, H., Doi, T.: Robot Entertainment, ch. 2. In: Druin, A., Hendler, J. (eds.) Robots for kids: exploring new technologies for learning, pp. 37–70. Morgan Kaufmann, San Francisco (2000)Google Scholar
  9. 9.
    Henrion, M.: Propagating uncertainty in Bayesian networks by logic sampling. Uncertainty in Artificial Intelligence 2, 149–163 (1988)Google Scholar
  10. 10.
    Jensen, F.V.: Bayesian Networks and Decision Graphs. Springer, Heidelberg (2001)MATHGoogle Scholar
  11. 11.
    Kanda, S., Murase, Y., Fujioka, K.: Internet-based Robot: Mobile Agent Robot of Next-generation (MARON-1), vol. 54, pp. 285–292 (2003) (in Japanese)Google Scholar
  12. 12.
    Kanoh, M., Kato, S., Itoh, H.: Facial expressions using emotional space in sensitivity communication robot “ifbot”. In: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2004), pp. 1586–1591 (2004)Google Scholar
  13. 13.
    Sjölander, K.: The Snack Sound Toolkit, http://www.speech.kth.se/snack/
  14. 14.
    Kato, S., Ohsiro, S., Watabe, K., Itoh, H., Kimura, K.: A domestic robot with sensitive communication and its vision system for talker distinction. Intelligent Autonomous Systems 8, 1162–1168 (2004)Google Scholar
  15. 15.
    Kato, S., Ohshiro, S., Itoh, H., Kimura, K.: Development of a communication robot ifbot. In: IEEE International Conference on Robotics and Automation (ICRA 2004), pp. 697–702 (2004)Google Scholar
  16. 16.
    Korb, K.B., Nicholson, A.E.: Bayesian Artificial Intelligence. Chapman & Hall/CRC, Boca Raton (2003)CrossRefGoogle Scholar
  17. 17.
    Business Design Laboratory Co. Ltd. The Extremely Expressive Communication Robot, Ifbot, http://www.business-design.co.jp/en/product/001/index.html
  18. 18.
    Murase, Y., Yasukawa, Y., Sakai, K., et al.: Design of a compact humanoid robot as a platform (in Japanese). In: Proc. of the 19-th conf. of Robotics Society of Japan, Japan, pp. 789–790 (2001), http://pr.fujitsu.com/en/news/2001/09/10.html
  19. 19.
    Murphy, K.P.: Bayes Net Toolbox, http://www.cs.ubc.ca/~murphyk/Software/BNT/bnt.html
  20. 20.
    Murphy, K.P., Weiss, Y., Jordan, M.I.: Loopy belief propagation for approximate inference: an empirical study, 467–475 (1999)Google Scholar
  21. 21.
    Pearl, J.: Probabilistic Reasoning in Intelligent Systems. Morgan Kaufmann, San Francisco (1988)Google Scholar
  22. 22.
    Scherer, K.R., Johnstone, T., Klasmeyer, G.: Vocal expression of emotion. In: Davidson, R.J., Goldsmith, H., Scherer, K.R. (eds.) Handbook of the Affective Sciences, pp. 433–456. Oxford University Press, Oxford (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Shohei Kato
    • 1
  • Yoshiki Sugino
    • 1
  • Hidenori Itoh
    • 1
  1. 1.Dept. of Computer Science and EngineeringGraduate School of Engineering, Nagoya Institute of TechnologyNagoyaJapan

Personalised recommendations