Acoustic Analysis of voice samples to differentiate Healthy and Asthmatic persons

Abstract

Voice analysis for disease detection is a very important research topic in bio medical engineering. This process is non invasive and reliable. In this paper , For comparison of  asthma and healthy persons speech records of five vowels /a/, /i/, /e/, /o/, /u/ have been used. Some acoustic voice parameters jitter, shimmer, harmonic to noise ratio (HNR), noise to harmonic ratio (NHR) & mean  autocoorelation were extracted using PRAAT software. These parameters were then used to classify and   compare  the  asthmatic patients and healthy persons. In other words, these  features represents the particular voice and may be used for the comparison of healthy persons from unhealthy persons. This result suggests that the feasibility of the detection of  asthma disease through analyzing the various acoustic parameters of voice.