An Evaluation of Symbolic Feature Sets and Their Combination for Music Genre Classification

The automatic music genre classification task is an active area of research in the field of Music Information Retrieval. In this paper we use two different symbolic feature sets for genre classification and combine them using an early fusion approach. Our results show that early fusion achieves bett...

Full description

Saved in:
Bibliographic Details
Main Authors: Piccoli, Hanna C. B., Silla, Carlos N., De Leon, Pedro J. Ponce, Pertusa, Antonio
Format: Conference Proceeding
Language:English
Subjects:
Accuracy
Cultural differences
Feature extraction
Multiple signal classification
Music
Music information retrieval
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The automatic music genre classification task is an active area of research in the field of Music Information Retrieval. In this paper we use two different symbolic feature sets for genre classification and combine them using an early fusion approach. Our results show that early fusion achieves better classification accuracy than using any of the individual feature sets. Furthermore, when compared with some of the state of the art approaches using the same experimental conditions, early fusion of symbolic features is ranked the second best method.
ISSN:1062-922X
2577-1655
DOI:10.1109/SMC.2013.327