AES E-Library

M. Leimeister, "Feature Learning for Classifying Drum Components from Nonnegative Matrix Factorization," Paper 9261, (2015 May.). doi: M. Leimeister, "Feature Learning for Classifying Drum Components from Nonnegative Matrix Factorization," Paper 9261, (2015 May.). doi:
Abstract: This paper explores automatic feature learning methods to classify percussive components in nonnegative matrix factorization (NMF). To circumvent the necessity of designing appropriate spectral and temporal features for component clustering, as usually used in NMF-based transcription systems, multilayer perceptrons and deep belief networks are trained directly on the factorization of a large number of isolated samples of kick and snare drums. The learned features are then used to assign components resulting from the analysis of polyphonic music to the different drum classes and retrieve the temporal activation curves. The evaluation on a set of 145 excerpts of polyphonic music shows that the algorithms can efficiently classify drum components and compare favorably to a classic “bag-of-features” approach using support vector machines and spectral mid-level features.

@article{leimeister2015feature,
author={leimeister, matthias},
journal={journal of the audio engineering society},
title={feature learning for classifying drum components from nonnegative matrix factorization},
year={2015},
volume={},
number={},
pages={},
doi={},
month={may},} @article{leimeister2015feature,
author={leimeister, matthias},
journal={journal of the audio engineering society},
title={feature learning for classifying drum components from nonnegative matrix factorization},
year={2015},
volume={},
number={},
pages={},
doi={},
month={may},
abstract={this paper explores automatic feature learning methods to classify percussive components in nonnegative matrix factorization (nmf). to circumvent the necessity of designing appropriate spectral and temporal features for component clustering, as usually used in nmf-based transcription systems, multilayer perceptrons and deep belief networks are trained directly on the factorization of a large number of isolated samples of kick and snare drums. the learned features are then used to assign components resulting from the analysis of polyphonic music to the different drum classes and retrieve the temporal activation curves. the evaluation on a set of 145 excerpts of polyphonic music shows that the algorithms can efficiently classify drum components and compare favorably to a classic “bag-of-features” approach using support vector machines and spectral mid-level features.},}

TY - paper
TI - Feature Learning for Classifying Drum Components from Nonnegative Matrix Factorization
SP - EP -
AU - Leimeister, Matthias
PY - 2015
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - May 2015 TY - paper
TI - Feature Learning for Classifying Drum Components from Nonnegative Matrix Factorization
SP - EP -
AU - Leimeister, Matthias
PY - 2015
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - May 2015
AB - This paper explores automatic feature learning methods to classify percussive components in nonnegative matrix factorization (NMF). To circumvent the necessity of designing appropriate spectral and temporal features for component clustering, as usually used in NMF-based transcription systems, multilayer perceptrons and deep belief networks are trained directly on the factorization of a large number of isolated samples of kick and snare drums. The learned features are then used to assign components resulting from the analysis of polyphonic music to the different drum classes and retrieve the temporal activation curves. The evaluation on a set of 145 excerpts of polyphonic music shows that the algorithms can efficiently classify drum components and compare favorably to a classic “bag-of-features” approach using support vector machines and spectral mid-level features.