Each human being has a voice that is distinct and unique. Extraction and analysis of the features of a person’s voice plays a vital role in diagnosis of diseases in the recent years. The basic parameters used for the voice analysis are Fundamental Frequency (F0), Jitter, Shimmer and Harmonics-to-Noise Ratio. Most of the prevailing Voice Analysis Software are highly commercial with complicated User Interface, requiring expertise to operate them. Hence the proposed study is carried out, which led to the development of a Voice Analysis Application called ‘Ephphatha’. A novel algorithm with improvised measures for voice analysis is used in Ephphatha. The acoustic parameters of duly collected voice samples were analyzed by Ephphatha and compared with the existing algorithms like PRAAT and Multi-Dimensional Voice Program (MDVP) of CSL(Computerized Speech Lab), with F-test analysis. The result showed no significant difference in F0 (p>0.05), except for its Standard Deviation values (p<0.001). The Ratio Of Variance (ROV) is less than or equal to 1 for F0. The other parameters are not significantly correlated. Also it showed that the shimmer values are moderately correlated (p<0.05), when Ephphatha is compared with CSL. It was also seen that all the parameters of PRAAT and Ephphatha have no significance difference (P > 0.05), except for the Shimmer values (p<0.001). Thus Ephphatha would undoubtedly equip the experienced clinicians with its novel approach and better User Interface.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.