Pearson correlation coefficient for speech emotion recognition system using novel logistic regression algorithm and compare accuracy with support vector machines algorithm Available to Purchase

The objective of this study is to determine the Pearson correlation coefficients for systems that are able to recognize the feelings that are communicated through spoken language. This will be accomplished by contrasting the novel logistic regression technique with the current Support Vector Machines method.an examination of voice emotion recognition systems that use machine learning, comparing different algorithms and evaluating how accurate they are. Materials and methods: In order to forecast the tone of spoken language and obtain the best results when comparing algorithms, this study makes use of a new approach of logistic regression and the appropriate kernel function for recognition. Before beginning the speech, the program need to be able to deliver the precise feeling that is being sent. Twenty people make up each group, which is a sample size that is lower than the recommended sample size of eighty percent for carrying out the necessary work and conducting the necessary analysis. Results: In our experiments, we evaluated the Novel Logistic Regression approach using a support vector machine (SVM) prediction accuracy of 88.7% and a Pearson correlation coefficient prediction accuracy of 90.1%. The results of the independent samples t-tests indicate that there is a difference of 0.031 (p0.05) in terms of accuracy between the two algorithms. Conclusion: The Novel Logistic Regression method outperforms Support Vector Machines by a significant margin.