ISCA Archive Interspeech 2008
ISCA Archive Interspeech 2008

Automatic lip synchronization by speech signal analysis

Goranka Zoric, Aleksandra Cerekovic, Igor S. Pandzic

In this paper a system for the automatic lip synchronization of virtual 3D human based only on the speech input is described. The speech signal is classified into viseme classes using neural networks. Visual representation of phonemes, visemes, defined in MPEG-4 FA, is used for face synthesis.


Cite as: Zoric, G., Cerekovic, A., Pandzic, I.S. (2008) Automatic lip synchronization by speech signal analysis. Proc. Interspeech 2008, 2323

@inproceedings{zoric08_interspeech,
  author={Goranka Zoric and Aleksandra Cerekovic and Igor S. Pandzic},
  title={{Automatic lip synchronization by speech signal analysis}},
  year=2008,
  booktitle={Proc. Interspeech 2008},
  pages={2323}
}