Comparison of Different Talking Heads in Non-Interactive Settings

  • Benjamin Weiss
  • Christine Kühnel
  • Ina Wechsung
  • Sebastian Möller
  • Sascha Fagel
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5612)


Six different talking heads have been evaluated in two consecutive experiments. Two text-to-speech components and three head components have been used. Results from semantic differentials show a clear preference for the most human-like and expressive head. The analysis of the semantic differentials reveals three factors each. These factors show different patterns for the head components. Overall quality is strongly related to one factor, which covers the quality aspect ‘appearance’. Another factor found in both experiments comprises ‘human likeliness’ and ‘naturalness’ and is much less correlated with overall quality. While subjects have been able to clearly separate all head components with different factors of the semantic differential, only some of these factors are relevant for explicit quality ratings. A good appearance seems to affect the perception of sympathy and the ascription of reliability.


talking heads evaluation quality aspects smart home domain 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Adcock, A., Van Eck, R.: Reliability and factor structure of the attitude toward tutoring agent scale (ATTAS). Journal of Interactive Learning Research 16(2), 195–217 (2005)Google Scholar
  2. 2.
    Beskow, J.: Rule-Based Speech Synthesis. In: Proc. Eurospeech, pp. 299–302 (1995)Google Scholar
  3. 3.
    Burnham, D., Abrahamyan, A., Cavedon, L., Davis, C., Hodgins, A., Kim, J., Kroos, C., Kuratate, T., Lewis, T., Luerssen, M., Paine, G., Powers, D., Riley, M., Stelarc, S.K.: From talking to thinking heads: 2008. In: Proc. AVSP, Tangalooma (2008)Google Scholar
  4. 4.
    Cohen, M.M., Massaro, D.W.: Modeling coarticulation in synthetic visual speech. In: Thalmann, N.M., Thalmann, D. (eds.) Models and techniques in computer animation, pp. 139–156. Springer, Tokyo (1993)CrossRefGoogle Scholar
  5. 5.
    Dutoit, T., Pagel, V., Pierret, N., Bataille, F., Van der Vreken, O.: The MBROLA Project: Towards s set of high-quality speech synthesizers free of use for non-commercial purposes. In: Proc. ICSLP, pp. 1393–1396 (1996)Google Scholar
  6. 6.
    Fagel, S., Bailly, G., Elisei, F.: Intelligibility of natural and 3D-cloned German speech. In: Proc. AVSP, Hilvarenbeek (2007)Google Scholar
  7. 7.
    Fagel, S., Clemens, C.: An articulation model for audiovisual speech synthesis – determination, adjustment, evaluation. Speech Communication 44, 141–154 (2004)CrossRefGoogle Scholar
  8. 8.
    Foster, M.E.: Enhancing human-computer interaction with embodied conversational agents. In: Proc. HCI International, Beijing (2007)Google Scholar
  9. 9.
    Horn, J.: A rationale and a test for the number of factors in factor analysis. Psychometrika 30, 179–185 (1965)CrossRefGoogle Scholar
  10. 10.
    Hutcheson, G., Sofroniou, N.: The multivariate social scientist. Sage Publications, Thousand Oaks (1999)CrossRefzbMATHGoogle Scholar
  11. 11.
    Krämer, N.C.: Soziale Wirkungen virtueller Helfer: Gestaltung und Evaluation von Mensch-Computer-Interaktion. Kohlhammer, Stuttgart (2008)Google Scholar
  12. 12.
    Kühnel, C., Weiss, B., Wechsung, I., Fagel, S., Möller, S.: Evaluating Talking Heads for Smart Home Systems. In: Proc. ICMI, Chania (2008)Google Scholar
  13. 13.
    Osborne, J., Costello, A.: Best Practices in Exploratory Factor Analysis: Four Recommendations for Getting the Most From Your Analysis. Practical Assessment Research and Evaluation 10(5), 1–9 (2005)Google Scholar
  14. 14.
    Ruttkay, Z., Pelachaud, C.: From Brows to Trust: Evaluating Embodied Conversational Agents. Springer, New York (2004)CrossRefzbMATHGoogle Scholar
  15. 15.
    Schroeder, M., Trouvain, J.: The German text-to-speech synthesis system MARY: A tool for research, development and teaching. International Journal of Speech Technology 6, 365–377 (2003)CrossRefGoogle Scholar
  16. 16.
    Yee, N., Bailenson, J.N., Rickertsen, K.: A meta-analysis of the impact of the inclusion and realism of human-like faces on user experiences in interfaces. In: Proc. SIGCHI, San José (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Benjamin Weiss
    • 1
  • Christine Kühnel
    • 1
  • Ina Wechsung
    • 1
  • Sebastian Möller
    • 1
  • Sascha Fagel
    • 2
  1. 1.Quality & Usability Lab, Deutsche Telekom LaboratoriesTechnische Universität BerlinBerlinGermany
  2. 2.Department for Language & CommunicationTechnische Universität BerlinBerlinGermany

Personalised recommendations