DISCRIMINATIVE METRIC DESIGN FOR ROBUST PATTERN-RECOGNITION

Motivated by the development of discriminative feature extraction (DFE ), many researchers have come to realize the importance of designing a front-end feature extraction unit with an appropriate link to backend classification. This paper proposes an advanced formalization of DFE, which we call the discriminative metric design (DR;ID), and elaborate s on its exemplar implementation by using a simple, linear feature tra nsformation matrix. The resulting DMD implementation is shown to have a close relationship to various discriminative pattern recognizers, in cluding artificial neural networks. The utility of the proposed method is clearly demonstrated in speech pattern recognition experiments.