MACHINE LEARNING TECHNIQUES APPLIED TO MUSICAL GENRE RECOGNITION
Daniel Boxler · Digital Collections of Colorado (Colorado State University) · 2020
With the wealth of music available at the fingertips of users around the world, there is an ever-increasing need for automatic classification of music for cataloguing of music for organization and quicker retrieval which is often done manually by experts in the field.To further complicate the issue, there is no standard definition on what determines a song's genre, which can be a culmination of various themes and moods that the song generates in listeners.This work designs and evaluates several models using Deep Neural Networks and Gradient Boosting Machines, using various transformations of the raw audio for predicting the genre of a particular piece of music.In particular, this research involves adapting the natural taxonomy of musical genres to generate a machine learning model in an attempt to capture some of the natural hierarchy in music.The results show that gradient boosting machines outperform all other models in terms of loss and accuracy.