An automatic diagnostic system for medically disordered voice
Mansour Alsulaiman, Ghulam Muhammad, Mohammed Azeez Alomari, Mohammed Alshehri, Zulfiqar Ali, Awais Mahmood · 2011
Abstract- The automatic detection of vocal cord/vocal tract diseases from the medically disordered speech is a challenging task in the medical field. An automatic diagnostic system for the medically disordered voice is proposed in this paper. The developed system takes speech recorded by a patient having a disorder in his/her voice, as an input. The system gives the type of voice disorder as an output. The output is accompanied by a confidence score that tells about the systems confidence of correctly recognizing the type of the disorder as output. In the system, after the detection of the vowels from the disordered speech, two formants F1 and F2 are extracted from the vowels and Euclidean distance is used for classification. The results of the proposed system are encouraging.