Comparison of spectrogram scaling in multi-label Music Genre Recognition
Bartosz Karpiński, Cyryl Leszczyński
2025-06-02Music Genre Recognition
Abstract
As the accessibility and ease-of-use of digital audio workstations increases, so does the quantity of music available to the average listener; additionally, differences between genres are not always well defined and can be abstract, with widely varying combinations of genres across individual records. In this article, multiple preprocessing methods and approaches to model training are described and compared, accounting for the eclectic nature of today's albums. A custom, manually labeled dataset of more than 18000 entries has been used to perform the experiments.
Related Papers
Comparing the Accuracy of Deep Neural Networks (DNN) and Convolutional Neural Network (CNN) in Music Genre Recognition (MGR): Experiments on Kurdish Music2021-11-22Wasserstein Barycenter for Multi-Source Domain Adaptation2021-06-19Client-driven Animated GIF Generation Framework Using an Acoustic Feature2021-02-12SAD: Saliency-based Defenses Against Adversarial Examples2020-03-10Learning Discrete Structures for Graph Neural Networks2019-03-28Machine learning and chord based feature engineering for genre prediction in popular Brazilian music2019-02-08Bottom-up Broadcast Neural Network For Music Genre Classification2019-01-24Extended pipeline for content-based feature engineering in music genre recognition2018-05-12