Please use this identifier to cite or link to this item:

Title: Instrumentals/songs separation for background music removal
Authors: Mukherjee, Himadri
Obaidullah, Sk
Santosh, K.C.
Phadikar, Santanu
Gonçalves, Teresa
Roy, Kaushik
Keywords: Background track
Line Spectral Pair
Issue Date: 2018
Publisher: Springer
Citation: Himadri Mukherjee, Sk Md Obaidullah, K.C. Santosh, Teresa Goncalves, Santanu Phadikar, and Kaushik Roy. Instrumentals/songs separation for background music removal. In ITSRCP’2018 – 3rd Conference on Information Technology, Computational and Experimental Physics, volume (to appear) of Advances in Intelligent Systems and Computing, page (to appear). Springer, 2018.
Abstract: The music industry has come a long way since its inception. Music producers have also adhered to modern technology to infuse life into their creations. Systems capable of separating sounds based on sources especially vocals from songs have always been a necessity which has gained attention from researchers as well. The challenge of vocal separation elevates even more in the case of the multi-instrument environment. It is essential for a system to be first able to detect that whether a piece of music contains vocals or not prior to attempting source separation. In this paper, such a system is proposed being tested on a database of more than 99 hours of instrumentals and songs. Using the line spectral frequency-based features, we have obtained the highest accuracy of 99.78% from among six different classifiers, viz. BayesNet, support vector machine, multi layere perceptron, liblinear, simple logistic and decision table.
Type: article
Appears in Collections:INF - Publicações - Artigos em Revistas Internacionais Com Arbitragem Científica

Files in This Item:

File Description SizeFormat
2018mukherjee-instrumental.pdf771.69 kBAdobe PDFView/OpenRestrict Access. You can Request a copy!
FacebookTwitterDeliciousLinkedInDiggGoogle BookmarksMySpaceOrkut
Formato BibTex mendeley Endnote Logotipo do DeGóis 

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.


Dspace Dspace
DSpace Software, version 1.6.2 Copyright © 2002-2008 MIT and Hewlett-Packard - Feedback
UEvora B-On Curriculum DeGois