Normal versus pathological voice signals

In this work, a method to analyze the time-frequency characteristics to distinguish pathological voices from patients with Reinke's edema and nodules in vocal folds was developed. Daubechies discrete wavelet transform (DWT) components of approximation and detail in convenient scales of frequency for different voice signals were used to analyze the time-frequency signal characteristics. In this work, 71 voice signals were used from subjects of different ages, both male and female: 30 with no pathology in vocal folds, 25 from patients with nodules in vocal folds, and 16 from patients with Reinke's edema. Least squares support-vector machines (LS- SVM) classifier leads to more than 90% of classification accuracy between normal voices and voices from patients with nodules in vocal folds, more than 85% between normal voices and voices from patients with Reinke's edema, and more than 80% between the two different pathological voice signals.