Frame Blocking Technique for Speech Emotion Recognition Using Novel Logistic Regression Algorithm Compared with Decision Tree Algorithm for Accuracy

The goal is to identify speech emotions through the use of the frame blocking technique in order to maximize data quality efficiency. This is done by comparing the accuracy of the decision tree algorithm with the novel logistic regression technique. Speech emotion recognition systems employ machine learning algorithms that are compared for accuracy. putting the method into practice, choosing the optimum kernel function for speech recognition, and applying the logistic regression technique algorithm to predict speech emotion and obtain the greatest algorithmic accuracy. The algorithm must to be sufficiently effective to generate the precise speech emotion prior to the speech commencing. Twenty is the sample size for each of the two groups, and 80 % of the sample size is taken into consideration when carrying out the work and analysis. The G-Power value of 0.8 was taken into consideration while determining the significance value of the dataset using SPSS. With an accuracy of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{8 3. 3 \%}$</tex> and <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{9 0. 1 \%}$</tex>, respectively, a novel logistic regression algorithm was developed for an effective frame blocking strategy and decision tree. The statistically significant 2 -tailed difference in accuracy between the two algorithms is <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$0.00(p&lt;0.05)$</tex>, according to independent samples t-tests. The new logistic regression strategy outperforms the decision tree technique by a significant margin.