A Theoretical Framework for a User-Centered Spoken Dialog Manager

  • Stefan UltesEmail author
  • Tobias Heinroth
  • Alexander Schmitt
  • Wolfgang Minker
Conference paper


Dialog strategies have long since been handcrafted by dialog experts. Only within the last decade, research has moved to data-driven methods leading to statistical models. But still, most dialog systems make use solely of the spoken words and their semantics, although speech signals reveal much more about the speaker, e.g. its age, gender, emotional state, etc. Using this speaker state information - along with the semantics - can be a promising way of moving dialog systems towards better performance whilst making them more natural at the same time. Partially Observable Markov Decision Processes (POMDPs), a state-of-the-art statistical modeling method, offer an easy and unified way of integrating speaker state information into dialog systems. In this contribution we present our ongoing research on combining a POMDP-based dialog manager with speaker state information.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Abdulla, W.H., Kasabov, N.K.: Improving speech recognition performance through gender separation. In: Proc. of ANNES, pp. 218–222 (2001)Google Scholar
  2. 2.
    Bohus, D., Raux, A., Harris, T.K., Eskenazi, M., Rudnicky, A.I.: Olympus: an open-source framework for conversational spoken language interface research. In: Proc. of, NAACL-HLT-Dialog ’07, pp. 32–39 (2007)Google Scholar
  3. 3.
    Heinroth, T., Denich, D.: Spoken interaction within the computed world: Evaluation of a multitasking adaptive spoken dialogue system (2011). CompsacGoogle Scholar
  4. 4.
    Holzapfel, H.: A dialogue manager for multimodal human-robot interaction and learning of a humanoid robot. Industrial Robot: An International Journal 35(6), 528–535 (2008)CrossRefGoogle Scholar
  5. 5.
    Kaelbling, L.P., Littman, M.L., Cassandra, A.R.: Planning and acting in partially observable stochastic domains. Artificial Intelligence 101(1–2), 99–134 (1998)MathSciNetzbMATHCrossRefGoogle Scholar
  6. 6.
    Larsson, S., Traum, D.: Information state and dialogue management in the trindi dialogue move engine. Natural Language Engineering Special Issue 6, 323–340 (2000)CrossRefGoogle Scholar
  7. 7.
    Oshry, M., Auburn, R., Baggia, P., Bodell, M., Burke, D., Burnett, D., Candell, E., Carter, J., Mcglashan, S., Lee, A., Porter, B., Rehor, K.: Voice extensible markup language (voicexml) version 2.1 (2007)Google Scholar
  8. 8.
    Polzehl, T., Schmitt, A., Metze, F.: Salient features for anger recognition in german and english ivr portals. In: Spoken Dialogue Systems Technology and Design, pp. 83–105. Springer New York (2011)Google Scholar
  9. 9.
    Schmitt, A., Heinroth, T., Bertrand, G.: Towards emotion, age- and genderaware voicexml applications. In: Proc. of IE’09 (2009)Google Scholar
  10. 10.
    Schmitt, A., Polzehl, T., Liscombe, J.: The influence of the utterance length on the recognition of aged voices. In: Proc. of LREC. Valetta, Malta (2010)Google Scholar
  11. 11.
    Thomson, B., Young, S.: Bayesian update of dialogue state: A POMDP framework for spoken dialogue systems. Computer Speech & Language 24(4), 562– 588 (2010)CrossRefGoogle Scholar
  12. 12.
    Williams, J., Young, S.: Partially observable markov decision processes for spoken dialog systems. Computer Speech and Language (21), 393–422 (2007)CrossRefGoogle Scholar
  13. 13.
    Young, S., Gasic, M., Keizer, S., Mairesse, F., Schatzmann, J., Thomson, B., Yu, K.: The hidden information state model: A practical framework for POMDP-based spoken dialogue management. Computer Speech & Language 24(2), 150–174 (2009)CrossRefGoogle Scholar
  14. 14.
    Young, S., Williams, J., Schatzmann, J., Stuttle, M., Weilhammer, K.: D4.3: Bayes net prototype - the hidden information state dialogue manager. Tech. rep., TALK project, IST-507802, 6th FP (2006)Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2011

Authors and Affiliations

  • Stefan Ultes
    • 1
    Email author
  • Tobias Heinroth
    • 1
  • Alexander Schmitt
    • 1
  • Wolfgang Minker
    • 1
  1. 1.Institute of Information TechnologyUlmGermany

Personalised recommendations