A Novel Pattern Learning and Recognition Procedure Applied to the Learning of Vowels

Abstract
The ability of a set of simple predicates to capture characteristic patterns in a parametric representation of vowels in continuous speech was investigated with the aid of an efficient conjunctive pattern recognition and classification system. The results compare favorably with those produced by a cluster-based minimal Euclidean distance technique, run over the identical training and test samples. The predicates used are similar to auditory receptive fields.

This publication has 0 references indexed in Scilit: