AES E-Library

M. Spiertz, and V. Gnann, "Beta Divergence for Clustering in Monaural Blind Source Separation," Paper 8130, (2010 May.). doi: M. Spiertz, and V. Gnann, "Beta Divergence for Clustering in Monaural Blind Source Separation," Paper 8130, (2010 May.). doi:
Abstract: General purpose audio blind source separation algorithms have to deal with a large dynamic range for the different sources to be separated. In our algorithm the mixture is separated into single notes. These notes are clustered to construct the melodies played by the active sources. The non-negative matrix factorization (NMF) leads to good results in clustering the notes according to spectral features. The cost function for the NMF is controlled by a parameter beta. The choice of beta depends on the dynamic difference of the sources. The novelty of this paper is to propose a simple classifier to adjust the parameter beta to current dynamic ranges for increasing the separation quality.

@article{spiertz2010beta,
author={spiertz, martin and gnann, volke and },
journal={journal of the audio engineering society},
title={beta divergence for clustering in monaural blind source separation},
year={2010},
volume={},
number={},
pages={},
doi={},
month={may},} @article{spiertz2010beta,
author={spiertz, martin and gnann, volke and },
journal={journal of the audio engineering society},
title={beta divergence for clustering in monaural blind source separation},
year={2010},
volume={},
number={},
pages={},
doi={},
month={may},
abstract={general purpose audio blind source separation algorithms have to deal with a large dynamic range for the different sources to be separated. in our algorithm the mixture is separated into single notes. these notes are clustered to construct the melodies played by the active sources. the non-negative matrix factorization (nmf) leads to good results in clustering the notes according to spectral features. the cost function for the nmf is controlled by a parameter beta. the choice of beta depends on the dynamic difference of the sources. the novelty of this paper is to propose a simple classifier to adjust the parameter beta to current dynamic ranges for increasing the separation quality.},}

TY - paper
TI - Beta Divergence for Clustering in Monaural Blind Source Separation
SP - EP -
AU - Spiertz, Martin
AU - Gnann, Volke
PY - 2010
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - May 2010 TY - paper
TI - Beta Divergence for Clustering in Monaural Blind Source Separation
SP - EP -
AU - Spiertz, Martin
AU - Gnann, Volke
PY - 2010
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - May 2010
AB - General purpose audio blind source separation algorithms have to deal with a large dynamic range for the different sources to be separated. In our algorithm the mixture is separated into single notes. These notes are clustered to construct the melodies played by the active sources. The non-negative matrix factorization (NMF) leads to good results in clustering the notes according to spectral features. The cost function for the NMF is controlled by a parameter beta. The choice of beta depends on the dynamic difference of the sources. The novelty of this paper is to propose a simple classifier to adjust the parameter beta to current dynamic ranges for increasing the separation quality.