Detection of degree of developmental dysphasia based on methods of vowel analysis

Our research involves an original method for the intensity of speech defect monitoring in child patients with developmental dysphasia. We have drawn upon a body of knowledge consisting of phonetics, acoustics and ANN applications. The aim of the paper is to compare two methods based on the vowel detector, both of which classify the parameter of developmental dysphasia, with the results of the speech therapist. Both methods create a model of vowel detector from data of healthy children and then the model classifies the vowels of children with developmental dysphasia. The first method is based on classical methods such as PCA and clustering. The KSOM were chosen for solving part of the project. The self-organizing maps are favourable for persons without an engineering background, primarily for the ability to visualize higher-dimensional data samples in a low-dimensional display.