Speech Emotion Recognition in Machine Learning to Improve Accuracy using Novel Support Vector Machine and Compared with Decision Tree Algorithm
DOI:
https://doi.org/10.47750/pnr.2022.13.S04.019Keywords:
Speech Emotion, Novel Support Vector Machine algorithm, Machine Learning, Decision Tree algorithm, .wav audio, Feature Extraction.Abstract
Aim: The aim of this research is to improve accuracy for speech emotion recognition using SVM algorithm and DT algorithm.
Materials and Methods: The research contains two groups namely SVM algorithm is developed in the first group and DT algorithm is developed in the second group contains 104 samples. The DT algorithm has a sample size of 52 whereas the SVM algorithm has a sample size of 52 and G power (value = 0.8).
Results: The performance has been improved in terms of accuracy for the SVM algorithm with 91% while the DT algorithm has shown an accuracy of 62%. The mean accuracy detection is ±2SD and the significant value is 0.0415(p<0.05) from an independent sample T test, which is statistically significant between two groups.
Conclusion: The final outcome of the SVM (91%) algorithm is found to be significantly more accurate than the DT algorithm(62%).
