Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Extended Pipeline for Content-Based Feature Engineering in Music Genre Recognition

Abstract: 

We present a feature engineering pipeline for the construction of musical signal characteristics, to be used for the design of a supervised model for musical genre identification. The key idea is to extend the traditional two-step process of extraction and classification with additive stand-alone phases which are no longer organized in a waterfall scheme. The whole system is realized by traversing backtrack arrows and cycles between various stages. In order to give a compact and effective representation of the features, the standard early temporal integration is combined with other selection and extraction phases: on the one hand, the selection of the most meaningful characteristics based on information gain, and on the other hand, the inclusion of the nonlinear correlation between this subset of features, determined by an autoencoder. The results of the experiments conducted on GTZAN dataset reveal a noticeable contribution of this methodology towards the model’s performance in the classification task.

up
0 users have voted:

Paper Details

Authors:
Alessandro Tibo, Paolo Bientinesi
Submitted On:
12 April 2018 - 2:00pm
Short Link:
Type:
Poster
Event:
Presenter's Name:
Tina Raissi
Paper Code:
MLSP-P6
Document Year:
2018
Cite

Document Files

Feature_Engineering_Pipeline

(253 downloads)

Subscribe

[1] Alessandro Tibo, Paolo Bientinesi, "Extended Pipeline for Content-Based Feature Engineering in Music Genre Recognition", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2459. Accessed: Aug. 21, 2018.
@article{2459-18,
url = {http://sigport.org/2459},
author = {Alessandro Tibo; Paolo Bientinesi },
publisher = {IEEE SigPort},
title = {Extended Pipeline for Content-Based Feature Engineering in Music Genre Recognition},
year = {2018} }
TY - EJOUR
T1 - Extended Pipeline for Content-Based Feature Engineering in Music Genre Recognition
AU - Alessandro Tibo; Paolo Bientinesi
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2459
ER -
Alessandro Tibo, Paolo Bientinesi. (2018). Extended Pipeline for Content-Based Feature Engineering in Music Genre Recognition. IEEE SigPort. http://sigport.org/2459
Alessandro Tibo, Paolo Bientinesi, 2018. Extended Pipeline for Content-Based Feature Engineering in Music Genre Recognition. Available at: http://sigport.org/2459.
Alessandro Tibo, Paolo Bientinesi. (2018). "Extended Pipeline for Content-Based Feature Engineering in Music Genre Recognition." Web.
1. Alessandro Tibo, Paolo Bientinesi. Extended Pipeline for Content-Based Feature Engineering in Music Genre Recognition [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2459