Carreira-Perpinan, Miguel A

Renals, Steve

24

2006-05-15T12:19:03Z

2006-05-15T12:19:03Z

1998-12

We consider the problem of obtaining a reduced dimension representation of electropalatographic (EPG) data. An unsupervised learning approach based on latent variable modelling is adopted, in which an underlying lower dimension representation is inferred directly from the data. Several latent variable models are investigated, including factor analysis and the generative topographic mapping (GTM). Experiments were carried out using a subset of the EUR-ACCOR database, and the results indicate that these automatic methods capture important, adaptive structure in the EPG data. Nonlinear latent variable modelling clearly outperforms the investigated linear models in terms of log-likelihood and reconstruction error and suggests a substantially smaller intrinsic dimensionality for the EPG data than that claimed by previous studies. A two-dimensional representation is produced with applications to speech therapy, language learning and articulatory dynamics.

574055 bytes

application/pdf

Speech Communication (1998) 26, 259-282.

0167-6393

http://dx.doi.org/10.1016/S0167-6393(98)00059-4

http://hdl.handle.net/1842/1072

en

Elsevier

Electropalatography

Articulatory modelling

Data reduction methods

Dimensionality reduction

Latent variable models

Finite mixture distributions

Mixture models

Principal component analysis

Factor analysis

Mixtures of factor analysers

Generalised topographic mapping

Mixtures of multivariate Bernoulli distributions

Dimensionality reduction of electropalatographic data using latent variable models

Article