On the Automatic Classification of Reading Disorders

In this paper, we present an automatic classification approa ch to identify reading disorders in children. This identification is b ased on a standardized test. In the original setup the test is performed by a human su pervisor who measures the reading duration and notes down all reading errors of the child at the same time. In this manner we recorded tests of 38 children who were suspected to have reading disorders. The data was confronted to an auto m tic system which employs speech recognition to identify the reading errors. In a subsequent classification experiment — based on the speech recognizer’s outpu t and the duration of the test — 94.7 % of the children could be classified correct ly.