Analysis of Audio Data and Prediction of the Genre using Novel Random Forest and Decision Tree

The main objective of the study is to classify the music genre using the features that are extracted from audio files. The classification is done using Novel Random Forest and Decision Tree and corresponding results are compared in terms of accuracy. Materials and Methods: The GTZAN dataset used in this study is obtained from the MARSYAS website, which is used for Music Information Retrieval, consists of 1000 music files in the .au format. It is also referred to as the standard dataset to the date. The acoustic features of music called Mel-frequency cepstral coefficients(MFCC) that create patterns and help to predict the genre are extracted from the Music files. The data analysis, model training, and testing process are done entirely on the Jupyter platform. The Sample size was 20 per group. The pretest power obtained was 0.08. Results: From the experimental results it is observed that Novel Random forest gives an accuracy of 71.78% while Decision tree gives an accuracy of 59.89%. The classification process is done with both Novel Random Forest and Decision Tree, where the sample size N is 20 for two groups proposed (N=20) and comparison (N=20). The pretest power obtained is 0.08. Conclusion: In this study, it is found that the Random Forest model outperforms the Decision tree model in terms of accuracy by predicting the music genre efficiently.