Detection and Analysis of Emotion Recognition from Speech Signals using K-nearest Neighbours and comparing with Support Vector Machine

The purpose of this research is to evaluate the performance of the K-Nearest Neighbors (KNN) and Support Vector Machine (SVM) classifiers when it comes to identifying feelings based on speech inputs. Both the Materials and the Methods: A KNN and an SVM classifier are used to analyse speech signals from 20 different samples from each group to determine an individual's emotional state. A novel part of the work is that key characteristics can be extracted from speech signals and identified. The results show that the KNN classifier has an accuracy of 45.13% when it comes to the classification of emotions, while the SVM only has an accuracy of 27.18%. According to the results of the statistical analysis performed with SPSS, there is a substantial gap between the two groups (p 0.05). The findings of this study indicate that the accuracy of the KNN classifier is substantially higher than that of the SVM classifier when it comes to identifying human emotions.