Intelligent Music Genre Classification Using Acoustic Features via Machine Learning and Deep Learning Methods

Abstract

Nowadays, music genre classification has become increasingly important in the big data era and has become a critical area for many companies and research institutions. However, deciding which acoustic features to use most efficiently in classification and making fast and accurate predictions on large datasets is a significant challenge. In this study, the main purpose is to present a model that examines and classifies the sounds as quickly as possible while satisfying the accuracy level with new approaches. Modern machine learning and deep learning techniques are used to classify music genres, and comparisons are made on the GTZAN dataset in terms of accuracy and processing time with intelligent decision mechanisms. In addition, some advanced acoustic features that have not been used before are used to improve the classification performance. The proposed approach can be applied to sound classification problems in different industries. This study demonstrates the effectiveness of intelligent and data-driven systems in music genre classification, providing a reference for future research in the field of large-scale sound analysis.