This paper provides a way to classify vocal disorders for clinical applicat
ions. This goal is achieved by means of geometric signal separation in a fe
ature space. Typical quantities from chaos theory (like entropy, correlatio
n dimension and first lyapunov exponent) and some conventional ones (like a
utocorrelation and spectral factor) are analysed and evaluated, in order to
provide entries for the feature vectors. A way of quantifying the amount o
f disorder is proposed by means of a healthy index that measures the distan
ce of a voice sample from the centre of mass of both healthy and sick clust
ers in the feature space. A successful application of the geometrical signa
l separation is reported, concerning distinction between normal and disorde
red phonation. (C) 2000 IPEM. Published by Elsevier Science Ltd. All rights
reserved.