In this paper, various methods of heart beat variability assessment from speech analysis have been presented. Heart rate variability (HRV) is a physiological phenomenon where the time interval between heart beats varies. It is measured by the variation in the beat-to-beat interval. The present work deals with the HRV detection from speech parameters. RR-cycle detects one heart beat. Continuous monitoring of electrocardiograph for a span of time can provide HRV. More than 250 samples of normal informants as well as heart patients with enlarged heart have been collected during the four years of research work. The regular ECG and speech samples of the patient have been collected and analyzed. Further they had compared with the parameters of a normal healthy informant. Speech samples were collected through a microphone and subjected to be digitized. The required speech segmental have been extracted and analyzed through a DSP tool, PRAAT. ECG sample has been recorded through an ECG machine. A technique of HRV detection from speech analysis has been presented in this paper. The HRV detection from speech can be a very helpful tool in monitoring the functioning of human heart.
An electrocardiogram (ECG) is a test that records the electrical activity of the heart. ECG is also used to measure the rate and regularity of heart beats and can be correlated to blood pressure measurement. This paper describes a technique of the determination of systole and diastole cycle duration from the RR-cycle as well as effect of systole and diastole cycle variation on heart beat rate using speech parameters. The formant F2 and F3 characterize different emotional states like anger and fear. One heart beat includes one systole and one diastole cycle. In an electrocardiogram, electrical systole of the ventricles begins at the beginning of the QRS complex. Diastolic variation occurs after the systole cycle. RT interval describes systole cycle duration. The ECG, and the speech sample of several informants have been recorded simultaneously to obtain the required relationship.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.