Speech trajectory recognition in SOFM by using Bayes theorem

Author

He, Jun ; Leich, Henri

Author_Institution

Lab. TCTS, Mons Polytech., Belgium

fYear

1994

fDate

13-16 Apr 1994

Firstpage

109

Abstract

Trajectory of a speech signal on a self-organizing feature map (SOFM) is usually obtained by concatenating the cells with peak neural excitation given each input vector. This usually causes unsmooth trajectory of speech. We introduce a new method, solidly grounded on Bayes rule, to find the response trajectory in SOFM. It takes into account not only the present response of the cells given input vector but also the a priori information of the response in SOFM for each class. To test the effectiveness of this method, a Multilayer Perceptron (MLP) is used to classify the trajectory to the class it belongs to. It will be shown experimentally that with our new method the recognition rate is increased from 91.6% to 96.2%

Keywords

Bayes methods; feedforward neural nets; self-organising feature maps; speech recognition; Bayes rule; Bayes theorem; MLP; SOFM; input vector; multilayer perceptron; peak neural excitation; recognition rate; response; self-organizing feature map; speech signal; speech trajectory recognition; trajectory classification; Helium; Multidimensional systems; Multilayer perceptrons; Network topology; Neural networks; Organizing; Speech enhancement; Speech recognition; Testing; Trajectory;

fLanguage

English

Publisher

ieee

Conference_Titel

Speech, Image Processing and Neural Networks, 1994. Proceedings, ISSIPNN '94., 1994 International Symposium on

Print_ISBN

0-7803-1865-X

Type

conf

DOI

10.1109/SIPNN.1994.344953

Filename

344953