
Dysphonia is the impairment of voice production as diagnosed by a clinician, often used interchangeably with the complaint of hoarseness, which is a symptom of altered voice quality. While many patients experience dysphonia as a natural part of the aging process, it can be a symptom of a serious underlying condition.
The goal of this project is to continue the work done by previous projects and try and improve the classification results by pre-processing the data in a different way than done previously. An algorithm that determines whether the patient is healthy or suffers from various voice disorders was developed. The algorithm will base its decision on features that will be extracted from patients’ audio samples acquired in the Carmel Medical Center. The most informative features will be fed to a classifier that will detect whether the patient suffers from voice disorder and which one it is.