Audio Processing using Pattern Recognition for Music Genre Classification

TL;DR

This paper applies machine learning techniques to classify music genres from audio features, achieving over 92% accuracy with neural networks, and aims to enhance music recommendation systems.

Contribution

It introduces a neural network-based approach for genre classification using key audio features, demonstrating superior performance over other algorithms.

Findings

ANN achieved 92.44% validation accuracy

Spectral features like MFCCs improved model performance

Neural networks outperformed Logistic Regression, KNN, and Random Forest

Abstract

This project explores the application of machine learning techniques for music genre classification using the GTZAN dataset, which contains 100 audio files per genre. Motivated by the growing demand for personalized music recommendations, we focused on classifying five genres-Blues, Classical, Jazz, Hip Hop, and Country-using a variety of algorithms including Logistic Regression, K-Nearest Neighbors (KNN), Random Forest, and Artificial Neural Networks (ANN) implemented via Keras. The ANN model demonstrated the best performance, achieving a validation accuracy of 92.44%. We also analyzed key audio features such as spectral roll-off, spectral centroid, and MFCCs, which helped enhance the model's accuracy. Future work will expand the model to cover all ten genres, investigate advanced methods like Long Short-Term Memory (LSTM) networks and ensemble approaches, and develop a web application for real-time genre classification and playlist generation. This research aims to contribute to improving music recommendation systems and content curation.