Improved approach to automatic detection of speech disorders based on the hidden Markov models approach

In the work algorithms commonly utilized in continu ous speech recognition systems were applied to dete ction of speech disorders. The used algorithms were briefly described and the final method of speech disorders tection was presented. The article includes the results of the short test performed in order to check the effectiv ness and accuracy of the method. The aim of the test was detection and c lassification of fricative phonemes prolongation on e of the most common speech disorders in the Polish language. It is worth emphasizing that this method enables detec tion of a category of speech disturbance (e.g. fricative, nas al, vowels, etc... prolongation), but also provides t he information about a specific phoneme being disturbed.