Walker Speed Adaptation in Gait Synthesis

  • Joëlle Tilmanne
  • Thierry Dutoit
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7660)


This paper presents a Hidden Markov Model based walk synthesizer, where the velocities of the synthesized walks are interpolations of the walk paces present in the training database. In a first stage, Trajectory Hidden Semi Markov Models (THSMM) of gait are trained for different subjects and different velocities, using a database of motion capture walk sequences. In a second stage, the parameters of the individual speed models are interpolated in order to synthesize walks with speeds not present in the training database. A qualitative user evaluation of the synthesized sequences shows that the naturalness of motions is preserved after linear interpolation and that the evaluators are sensible to the interpolated speed of the motion.


motion synthesis walk style HMM 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Tilmanne, J., Dutoit, T.: Continuous control of style through linear interpolation in HMM based stylistic walk synthesis. In: Proc. CW 2011, pp. 232–236 (2011)Google Scholar
  2. 2.
    Troje, N.F.: Retrieving information from human movement patterns. In: Understanding Events: How Humans See, Represent, and Act on Events, pp. 308–334 (2008)Google Scholar
  3. 3.
    Tilmanne, J., Dutoit, T.: Expressive Gait Synthesis Using PCA and Gaussian Modeling. In: Boulic, R., Chrysanthou, Y., Komura, T. (eds.) MIG 2010. LNCS, vol. 6459, pp. 363–374. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  4. 4.
    Uratasun, R., Glardon, P., Boulic, R., Thalmann, D., Fua, P.: Style-based Motion Synthesis. Computer Graphics Forum 23(4), 799–812 (2004)CrossRefGoogle Scholar
  5. 5.
    Shapiro, A., Cao, Y., Faloutsos, P.: Style components. In: Proc. of Graphics Interface, pp. 33–39 (2006)Google Scholar
  6. 6.
    Min, J., Liu, H., Chai, J.: Synthesis and editing of personalized stylistic human motion. In: Proceedings of SI3D, pp. 39–46 (2010)Google Scholar
  7. 7.
    Hsu, E., Pulli, K., Popovic, J.: Style Translation for Human Motion. In: Proc. SIGGRAPH 2005, pp. 1082–1089 (2005)Google Scholar
  8. 8.
    Wang, Y., Xie, L., Liu, Z., Zhou, L.: The SOMN HMM model and its application to automatic synthesis of 3d character animation. In: IEEE Conference on Systems, Man, and Cybernetics, pp. 4948–4952 (2006)Google Scholar
  9. 9.
    Brand, M., Hertzmann, A.: Style machines. In: Proc. SIGGRAPH 2000, pp. 183–192 (2000)Google Scholar
  10. 10.
    Yamazaki, T., Niwase, N., Yamagishi, J., Kobayashi, T.: Human Walking Motion Synthesis Based on Multiple Regression Hidden Semi-Markov Model. In: Proc. Conference on Cyberworlds, CW 2005, pp. 445–452 (2005)Google Scholar
  11. 11.
    Tilmanne, J., Sebbe, R., Dutoit, T.: A Database for Stylistic Human Gait Modeling and Synthesis. In: Proceedings of the eNTERFACE 2008 Workshop on Multimodal Interfaces, Paris, France, pp. 91–94 (August 2008)Google Scholar
  12. 12.
    IGS-190. Animazoo website,
  13. 13.
    Grassia, F.S.: Practical parameterization of rotations using the exponential map. Journal of Graphics Tools 3, 29–48 (1998)CrossRefGoogle Scholar
  14. 14.
    HTS working group: The HMM-based speech synthesis system (HTS) Version 2.1 (2010), (accessed)
  15. 15.
    Tilmanne, J., Moinet, A., Dutoit, T.: Hidden Markov Model based stylistic gait synthesis. Eurasip Journal on Advances in Signal Processing (2012)Google Scholar
  16. 16.
    Tokuda, K., Yoshimura, T., Masuko, T., Kobayashi, T., Kitamura, T.: Speech parameter generation algorithms for hmm-based speech synthesis. In: Proc. of ICASSP, pp. 1315–1318 (June 2000)Google Scholar
  17. 17.
    Yoshimura, T., Tokuda, K., Masuko, T., Kobayashi, T., Kitamura, T.: Duration modeling for HMM based speech synthesis. In: Proc. of ICSLP, pp. 29–32 (1998)Google Scholar
  18. 18.
    Yamagishi, J., Kobayashi, T., Nakano, Y., Ogata, K., Isogai, J.: Analysis of speaker adaptation algorithms for HMM-based speech synthesis and a constrained SMAPLR adaptation algorithm. IEEE TASLP 17(1), 66–83 (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Joëlle Tilmanne
    • 1
  • Thierry Dutoit
    • 1
  1. 1.TCTS Lab / Numediart InstituteUniversity of Mons (UMONS)MonsBelgium

Personalised recommendations