Can I read Music Genre Classification.. A Comparative Analysis of CNN and XGBoost Approaches With Mel-Frequency Cepstral Coefficients and Mel Spectrograms on EtoBox?

Music Genre Classification.. A Comparative Analysis of CNN and XGBoost Approaches With Mel-Frequency Cepstral Coefficients and Mel Spectrograms by akalbangkit is a document available to read on EtoBox.

What is Music Genre Classification.. A Comparative Analysis of CNN and XGBoost Approaches With Mel-Frequency Cepstral Coefficients and Mel Spectrograms about?

This study compares the performance of three models—CNN, VGG16 with fully connected layers, and XGBoost—for music genre classification using Mel-frequency cepstral coefficients (MFCCs) and Mel spectrograms. The results indicate that the XGBoost model utilizing 3-second MFCCs outperformed the others, achieving a testing accuracy of 97%. Additionally, data segmentation during preprocessing significantly improved CNN performance.

Author

akalbangkit

Language

EN