Improved Accuracy in Speech Recognition System for Detection of COVID-19 using Support Vector Machine and Comparing with Convolution Neural Network Algorithm
Rallapalli Jhansi, G. Uganya
Abstract
The objective of the research aims to detect Covid-19 patients by innovative speech recognition using a Support Vector Machine (SVM) and comparing accuracy with Convolutional Neural Network (CNN). Speech recognition using SVM is considered as group 1 and Convolutional Neural Network is considered as group 2, where each group has 20 samples. A T-test with 95% CI, G-power of 80%, and alpha=0.05 was used to compare the two sets of data. CNN achieves an accuracy of 87.5<sup>%</sup> and SVM achieves an accuracy of 92.5% with significance value 0.043 (P<0.05). Covid-19 prediction using an innovative speech recognition using SVM achieves significantly better accuracy than CNN.
Topics & Concepts
Support vector machineConvolutional neural networkComputer scienceArtificial intelligenceConvolution (computer science)Pattern recognition (psychology)Speech recognitionArtificial neural networkCoronavirus disease 2019 (COVID-19)AlgorithmInfectious disease (medical specialty)PathologyDiseaseMedicineCOVID-19 diagnosis using AISpeech and Audio ProcessingInfant Health and Development