Voice pathology detection by fuzzy logic

In this paper an efficient feature extraction methods and fuzzy logic based disorder assessment technique were used to investigate voice signals of patients suffering from functional dysphonia, hyperfunctional dysphonia, vocal cord paralysis and laryngitis. In this work, a vector made up from 28 acoustic parameters was an input for Principal Component Analysis, kernel Principal Component Analysis and Auto-associative Neural Network. Using S-shaped membership function of fuzzy logic, signals were clustered into 2 classes - healthy and pathology one. The amount of fuzzy membership of normal and pathological voice signals in their corresponding clusters was a measure to quantify the membership of the features of a particular class. In the end, S-shaped fuzzy logic method was used as a way of voice pathology detection. A classification accuracy up to 100 percent was achieved using initial 28 feature vector.