A HMM-Based Method for Vocal Fold Pathology Diagnosis
Acoustic analysis is a proper method in vocal fold pathology diagnosis so that it can complement and in some cases replace the other invasive, based on direct vocal fold observations methods. There are different approaches for vocal fold pathology diagnosis. This paper presents a method based on hidden markov model which classifies speeches into two classes: the normal and the pathological. Two hidden markov models are trained based on these two classes of speech and then the trained models are used to classify the dataset. The proposed method is able to classify the speeches with an accuracy of 93.75%. The results of this algorithm provide insights that can help biologists and computer scientists design high-performance system for detection of vocal fold pathology diagnosis.
Keywords: Vocal fold pathology diagnosis, Hidden Markov Model (HMM), Mel- Frequency-Cepstral-Coefficients (MFCCs), Fundamental frequency, Vector Quantization (VQ), LBG Algorithm
Download Full-Text
ABOUT THE AUTHORS
Vahid Majidnezhad
Department of Computer Engineering, Shabestar Branch, Islamic Azad University, Shabestar, Iran
Igor Kheidorov
Department of Computer Engineering, Shabestar Branch, Islamic Azad University, Shabestar, Iran
Vahid Majidnezhad
Department of Computer Engineering, Shabestar Branch, Islamic Azad University, Shabestar, Iran
Igor Kheidorov
Department of Computer Engineering, Shabestar Branch, Islamic Azad University, Shabestar, Iran
