Single channel music sound separation based on spectrogram decomposition and note classification
Wang, W and Mustafa, H (2011) Single channel music sound separation based on spectrogram decomposition and note classification In: CMMR 2010: 7th International Symposium, 2010-06-21 - 2010-06-24, Malaga, Spain.
Available under License : See the attached licence file.
Separating multiple music sources from a single channel mixture is a challenging problem. We present a new approach to this problem based on non-negative matrix factorization (NMF) and note classification, assuming that the instruments used to play the sound signals are known a priori. The spectrogram of the mixture signal is first decomposed into building components (musical notes) using an NMF algorithm. The Mel frequency cepstrum coefficients (MFCCs) of both the decomposed components and the signals in the training dataset are extracted. The mean squared errors (MSEs) between the MFCC feature space of the decomposed music component and those of the training signals are used as the similarity measures for the decomposed music notes. The notes are then labelled to the corresponding type of instruments by the K nearest neighbors (K-NN) classification algorithm based on the MSEs. Finally, the source signals are reconstructed from the classified notes and the weighting matrices obtained from the NMF algorithm. Simulations are provided to show the performance of the proposed system. © 2011 Springer-Verlag Berlin Heidelberg.
|Item Type:||Conference or Workshop Item (Paper)|
|Additional Information:||The original publication is available at http://www.springerlink.com|
|Divisions:||Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Vision Speech and Signal Processing|
|Depositing User:||Symplectic Elements|
|Date Deposited:||12 Oct 2012 15:14|
|Last Modified:||23 Sep 2013 19:29|
Actions (login required)
Downloads per month over past year