A two-level scheme for speaker identification is proposed. The first c
lassifier level is based on the self-organizing map (SOM) of Kohonen.
LPCC coefficients are used as input vectors for this classifier. LPCC
coefficients are passed again through the already trained SOMs and as
result the prototype distribution maps (PDMs) are obtained. The PDMs a
re the input for the second classifier level. The second level consist
s of multilayer perceptron (MLP) networks for each speaker. The first
level of the classifier is a preprocessing procedure for the second le
vel, where the final classification is made. The goal of the proposed
approach is to combine the advantages of the two type of networks into
one classification scheme in order to achieve higher identification a
ccuracy. The experiments show an increased accuracy of the proposed tw
o-level classifier, especially in the case of noise-corrupted signals.