Continuous Control of Style through Linear Interpolation in Hidden Markov Model Based Stylistic Walk Synthesis

@article{Tilmanne2011ContinuousCO,
  title={Continuous Control of Style through Linear Interpolation in Hidden Markov Model Based Stylistic Walk Synthesis},
  author={Jo{\"e}lle Tilmanne and Thierry Dutoit},
  journal={2011 International Conference on Cyberworlds},
  year={2011},
  pages={232-236}
}
In this work, we present a Hidden Markov Model (HMM) based stylistic walk synthesizer, where the synthesized styles are combinations or exaggerations of the walk styles present in the training database. In a first stage, Hidden Markov Models of eleven different styles of gait are trained, using a database of motion capture walk sequences. In a second stage, the probability density functions inside the stylistic models are interpolated or extrapolated in order to synthesize walks with styles or… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.

References

Publications referenced by this paper.
Showing 1-10 of 19 references

Hidden Markov Model based stylistic gait synthesis

  • J. Tilmanne, A. Moinet, T. Dutoit
  • submitted for publication, 2011.
  • 2011
1 Excerpt

The HTK Book (for HTK Version 3.4)

  • S. Young, G. Evermann, +9 authors P. Woodland
  • Entropic Cambridge Research Laboratory,
  • 2009
1 Excerpt

Similar Papers

Loading similar papers…