A Music Classification Model based on Metric Learning and Feature Extraction from MP3 Audio Files

TL;DR

This paper introduces a novel music classification model that uses metric learning and feature extraction from MP3 files, aiming to improve music similarity learning and enable personalized metrics for users.

Contribution

It proposes a new metric learning approach with structured prediction for music genre classification, incorporating MFCC features and PCA for dimensionality reduction.

Findings

Model shows promising accuracy compared to baseline algorithms

Experiments validate the effectiveness of the metric learning approach

Encourages development of an online learning version

Abstract

The development of models for learning music similarity and feature extraction from audio media files is an increasingly important task for the entertainment industry. This work proposes a novel music classification model based on metric learning and feature extraction from MP3 audio files. The metric learning process considers the learning of a set of parameterized distances employing a structured prediction approach from a set of MP3 audio files containing several music genres. The main objective of this work is to make possible learning a personalized metric for each customer. To extract the acoustic information we use the Mel-Frequency Cepstral Coefficient (MFCC) and make a dimensionality reduction with the use of Principal Components Analysis. We attest the model validity performing a set of experiments and comparing the training and testing results with baseline algorithms, such as K-means and Soft Margin Linear Support Vector Machine (SVM). Experiments show promising results and encourage the future development of an online version of the learning model.