Neural Network Music Genre Classification

Music genre classification utilizing neural networks (NNs) has achieved some limited success in recent years. Differences in song libraries, machine learning techniques, input formats, and types of NNs implemented have all had varying levels of success. This article reviews some of the machine learn...

Full description

Saved in:
Bibliographic Details
Published inCanadian journal of electrical and computer engineering Vol. 43; no. 3; pp. 170 - 173
Main Authors Pelchat, Nikki, Gelowitz, Craig M.
Format Journal Article
LanguageEnglish
Published Montreal IEEE Canada 01.01.2020
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Artificial neural networks
Classification
convolutional neural network (CNN)
deep learning
Feature extraction
Genre
Image classification
Machine learning
Modeling
Music
music genre
neural network (NN)
Neural networks
Spectrogram
Spectrograms
Training
Online AccessGet full text

Cover

More Information
Summary:Music genre classification utilizing neural networks (NNs) has achieved some limited success in recent years. Differences in song libraries, machine learning techniques, input formats, and types of NNs implemented have all had varying levels of success. This article reviews some of the machine learning techniques utilized in this area. It also presents research work on music genre classification. The research uses images of spectrograms generated from timeslices of songs as the input into an NN to classify the songs into their respective musical genres.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0840-8688
DOI:10.1109/CJECE.2020.2970144