ABSTRACT

This research delves into the realm of music genre classification, a vital component of music information retrieval and audio signal processing. With the proliferation of digital music libraries and the rise of online music streaming platforms, the need for automated and accurate music genre classification has become paramount. However, this task is challenging due to the subjective nature of genre perception and the intricate nature of music analysis.

This study leverages machine learning techniques and the GTZAN dataset to advance music genre classification. The research encompasses data collection, preprocessing, feature extraction, model training, and real-time prediction. It aims to address class imbalance issues and evaluates various machine learning algorithms, including Random Forest, Decision Tree, K-Nearest Neighbors, and Support Vector Machine, in the pursuit of high classification accuracy.

The significance of this research extends to enhancing music organization and recommendation systems, thus elevating user satisfaction on music streaming platforms. Furthermore, it provides valuable insights to the music industry, enabling genre-specific music production and advancing the fields of music information retrieval and audio signal processing.