4th International Conference on Spoken Language Processing

Philadelphia, PA, USA
October 3-6, 1996

A Comparative Study of Linear Feature Transformation Techniques for Automatic Speech Recognition

T. Eisele, Reinhold Haeb-Umbach, D. Langmann

Philips GmbH Forschungslaboratorien, Aachen, Germany

Although widely used, there are still open questions concerning which properties of Linear Discriminant Analysis (LDA) do account for its success in many speech recognition systems. In order to gain more insight into the nature of the transformation we compare LDA with mel-cepstral feature vectors with respect to the following criteria: decorrelation and ordering property, invariance under linear transforms, automatic learning of dynamical features, and data dependence of the transformation.

Full Paper

Bibliographic reference.  Eisele, T. / Haeb-Umbach, Reinhold / Langmann, D. (1996): "A comparative study of linear feature transformation techniques for automatic speech recognition", In ICSLP-1996, 252-255.