ISCA Archive ICSLP 1994
ISCA Archive ICSLP 1994

Analysis of non-linear speech generating dynamics

Paul A. Moakes, Steve W. Beet

This paper demonstrates that the non-linear system dynamics generating speech can be embedded in a low dimensional Euclidean space which resembles a manifold. Phoneme manifolds are extracted from the speech time series and compared using a radial basis function network to attempt speaker independent phoneme classification. The initial results are inconclusive but show promising results. Phoneme manifolds are also used for speech prediction resulting in a predictor which is able to achieve noise reduction equal to that of a nonlinear predictor but exhibits an improvement in the signal quality.


Cite as: Moakes, P.A., Beet, S.W. (1994) Analysis of non-linear speech generating dynamics. Proc. 3rd International Conference on Spoken Language Processing (ICSLP 1994), 1039-1042

@inproceedings{moakes94_icslp,
  author={Paul A. Moakes and Steve W. Beet},
  title={{Analysis of non-linear speech generating dynamics}},
  year=1994,
  booktitle={Proc. 3rd International Conference on Spoken Language Processing (ICSLP 1994)},
  pages={1039--1042}
}