A Nonlinearized Discriminant Analysis and its Application to Speech Impediment Therapy
Title | A Nonlinearized Discriminant Analysis and its Application to Speech Impediment Therapy |
Publication Type | Conference Paper |
Year of Publication | 2001 |
Authors | Kocsor A, Tóth L, Paczolay D |
Editor | |
Conference Name | Text, Speech and Dialogue : 4th International Conference, TSD 2001, LNAI vol. 2166 |
Pagination | 249-257 |
Date Published | September |
Publisher | Springer-Verlag GmbH |
Place Published | Zelezna Ruda, Czech Republic |
Abstract | This paper studies the application of automatic phoneme classification to the computer-aided training of the speech and hearing handicapped. In particular, we focus on how efficiently discriminant analysis can reduce the number of features and increase classification performance. A nonlinear counterpart of Linear Discriminant Analysis, which is a general purpose class specific feature extractor, is presented where the nonlinearization is carried out by employing the so-called 'kernel-idea'. Then, we examine how this nonlinear extraction technique affects the efficiency of learning algorithms such as Artificial Neural Network and Support Vector Machines. |