Unsupervised learning for speech motion editing

  title={Unsupervised learning for speech motion editing},
  author={Yong Cao and Petros Faloutsos and Fr{\'e}d{\'e}ric H. Pighin},
  booktitle={Symposium on Computer Animation},
We present a new method for editing speech related facial motions. Our method uses an unsupervised learning technique, Independent Component Analysis (ICA), to extract a set of meaningful parameters without any annotation of the data. With ICA, we are able to solve a blind source separation problem and describe the original data as a linear combination of two sources. One source captures content (speech) and the other captures style (emotion). By manipulating the independent components we can… CONTINUE READING
Highly Cited
This paper has 104 citations. REVIEW CITATIONS

4 Figures & Tables



Citations per Year

105 Citations

Semantic Scholar estimates that this publication has 105 citations based on the available data.

See our FAQ for additional information.