An audio-driven dancing avatar


We present a framework for training and synthesis of an audio-driven dancing avatar. The avatar is trained for a given musical genre using the multicamera video recordings of a dance performance. The video is analyzed to capture the time-varying posture of the dancer’s body whereas the musical audio signal is processed to extract the beat information. We consider two different marker-based schemes for the motion capture problem. The first scheme uses 3D joint positions to represent the body motion whereas the second uses joint angles. Body movements of the dancer are characterized by a set of recurring semantic motion patterns, i.e., dance figures. Each dance figure is modeled in a supervised manner with a set of HMM (Hidden Markov Model) structures and the associated beat frequency. In the synthesis phase, an audio signal of unknown musical type is first classified, within a time interval, into one of the genres that have been learnt in the analysis phase, based on mel frequency cepstral coefficients (MFCC). The motion parameters of the corresponding dance figures are then synthesized via the trained HMM structures in synchrony with the audio signal based on the estimated tempo information. Finally, the generated motion parameters, either the joint angles or the 3D joint positions of the body, are animated along with the musical audio using two different animation tools that we have developed. Experimental results demonstrate the effectiveness of the proposed framework.

This is a preview of subscription content, log in to check access.


  1. 1.

    Chen T (2001) Audiovisual speech processing. IEEE Signal Process Mag 18(1):9–21

    MATH  Article  Google Scholar 

  2. 2.

    Bregler C, Covell M, Slaney M (1997) Video rewrite: driving visual speech with audio. In: SIGGRAPH ’97: Proceedings of the 24th annual conference on computer graphics and interactive techniques, New York, NY, USA. ACM Press/Addison-Wesley, New York, pp 353–360

    Google Scholar 

  3. 3.

    Brand M (1999) Voice puppetry. In: SIGGRAPH ’99: Proceedings of the 26th annual conference on computer graphics and interactive techniques, New York, NY, USA. ACM Press/Addison-Wesley, New York, pp 21–28

    Google Scholar 

  4. 4.

    Li Y, Shum H (2006) Learning dynamic audio-visual mapping with input-output hidden Markov models. IEEE Trans Multimedia 8(3):542–549

    Article  Google Scholar 

  5. 5.

    Ofli F, Erzin E, Yemez Y, Tekalp AM (2007) Estimation and analysis of facial animation parameter patterns. In: IEEE International conference on image processing

  6. 6.

    Sargin ME, Erzin E, Yemez Y, Tekalp AM, Erdem AT, Erdem C, Ozkan M (2007) Prosody-driven head-gesture animation. IEEE Int Conf Acoustics Speech Signal Process 2:677–680

    Google Scholar 

  7. 7.

    Sargin ME, Aran O, Karpov A, Ofli F, Yasinnik Y, Wilson S, Erzin E, Yemez Y, Tekalp AM (2006) Combined gesture—speech analysis and speech driven gesture synthesis. In: IEEE international conference on multimedia and expo, pp 893–896

  8. 8.

    Bagci U, Erzin E (2007) Automatic classification of musical genres using inter-genre similarity. IEEE Signal Process Lett 14:521–524

    Article  Google Scholar 

  9. 9.

    Ehara Y, Fujimoto H, Miyazaki S, Tanaka S, Yamamoto S (1995) Comparison of the performance of 3d camera systems. Gait Posture 3:166–169

    Article  Google Scholar 

  10. 10.

    Ehara Y, Fujimoto H, Miyazaki S, Mochimaru M, Tanaka S, Yamamoto S (1997) Comparison of the performance of 3d camera systems II. Gait Posture 5:251–255

    Article  Google Scholar 

  11. 11.

    Bregler C, Malik J (1998) Tracking people with twists and exponential maps. In: IEEE international conference on computer vision and pattern recognition

  12. 12.

    Deutscher J, Reid I (2005) Articulated body motion capture by stochastic search. Int J Comput Vis 61:185–205

    Article  Google Scholar 

  13. 13.

    Canton-Ferrer C, Casas JR, Pardàs M (2005) Towards a Bayesian approach to robust finding correspondences in multiple view geometry environments. In: Lecture notes on computer science, vol 3515. Springer, Berlin, pp 281–289

    Google Scholar 

  14. 14.

    Arulampalam M, Maskell S, Gordon N, Clapp T (2002) A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking. IEEE Trans Signal Process 50(2):174–188

    Article  Google Scholar 

  15. 15.

    Young S (1993) The htk hidden Markov model toolkit: design and philosophy. Technical Report TR. 153, Speech Group, Department of Engineering, Cambridge University (UK)

  16. 16.

    Alonso M, David B, Richard G (2004) Tempo and beat estimation of music signals. In: International conference on music information retrieval

  17. 17.

    Balci K, Not E, Zancanaro M, Pianesi F (2007) Xface open source project and smil-agent scripting language for creating and animating embodied conversational agents. In: MULTIMEDIA ’07: Proceedings of the 15th international conference on Multimedia, New York, NY, USA. ACM Press, New York, pp 1013–1016

    Google Scholar 

Download references

Author information



Corresponding author

Correspondence to Ferda Ofli.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Ofli, F., Demir, Y., Yemez, Y. et al. An audio-driven dancing avatar. J Multimodal User Interfaces 2, 93–103 (2008).

Download citation


  • Multicamera motion capture
  • Audio-driven body motion synthesis
  • Dancing avatar animation