An algorithm for the automatic differentiation between the speech of normals and patients with Friedreich's ataxia based on the short-time fractal dimension

Abstract

In this paper, we describe an algorithm, based on acoustic pattern matching techniques, for providing an automatic, highly reliable distinction between normal and some kind of pathological speech (Friedreich's ataxia disease). For each utterance, the short-time fractal dimension parameter and, for comparison, the zero-crossing and energy ratio parameters are evaluated and used in the classification task by means of a dynamic programming procedure. Although all the parameters are able to differentiate the two groups, the fractal dimension parameter seems to provide a more reliable pattern classification than zero-crossing and energy ratio. Finally, we point out that, to the discrimination purpose, an accurate choice of the utterances to be pronounced by the subjects is to be considered.