Detection of Piano Pedaling Techniques on the Sustain Pedal
×
Cite This
Citation & Abstract
B. Liang, G. Fazekas, and MA. B.. Sandler, "Detection of Piano Pedaling Techniques on the Sustain Pedal," Paper 9812, (2017 October.). doi:
B. Liang, G. Fazekas, and MA. B.. Sandler, "Detection of Piano Pedaling Techniques on the Sustain Pedal," Paper 9812, (2017 October.). doi:
Abstract: Automatic detection of piano pedaling techniques is challenging as it is comprised of subtle nuances of piano timbres. In this paper we address this problem on single notes using decision-tree-based support vector machines. Features are extracted from harmonics and residuals based on physical acoustics considerations and signal observations. We consider four distinct pedaling techniques on the sustain pedal (anticipatory full, anticipatory half, legato full, and legato half pedaling) and create a new isolated-note dataset consisting of different pitches and velocities for each pedaling technique plus notes played without pedal. Experiment shows the effectiveness of the designed features and the learned classifiers for discriminating pedaling techniques from the cross-validation trails.
@article{liang2017detection,
author={liang, beici and fazekas, györgy and sandler, mark b.},
journal={journal of the audio engineering society},
title={detection of piano pedaling techniques on the sustain pedal},
year={2017},
volume={},
number={},
pages={},
doi={},
month={october},}
@article{liang2017detection,
author={liang, beici and fazekas, györgy and sandler, mark b.},
journal={journal of the audio engineering society},
title={detection of piano pedaling techniques on the sustain pedal},
year={2017},
volume={},
number={},
pages={},
doi={},
month={october},
abstract={automatic detection of piano pedaling techniques is challenging as it is comprised of subtle nuances of piano timbres. in this paper we address this problem on single notes using decision-tree-based support vector machines. features are extracted from harmonics and residuals based on physical acoustics considerations and signal observations. we consider four distinct pedaling techniques on the sustain pedal (anticipatory full, anticipatory half, legato full, and legato half pedaling) and create a new isolated-note dataset consisting of different pitches and velocities for each pedaling technique plus notes played without pedal. experiment shows the effectiveness of the designed features and the learned classifiers for discriminating pedaling techniques from the cross-validation trails.},}
TY - paper
TI - Detection of Piano Pedaling Techniques on the Sustain Pedal
SP -
EP -
AU - Liang, Beici
AU - Fazekas, György
AU - Sandler, Mark B.
PY - 2017
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - October 2017
TY - paper
TI - Detection of Piano Pedaling Techniques on the Sustain Pedal
SP -
EP -
AU - Liang, Beici
AU - Fazekas, György
AU - Sandler, Mark B.
PY - 2017
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - October 2017
AB - Automatic detection of piano pedaling techniques is challenging as it is comprised of subtle nuances of piano timbres. In this paper we address this problem on single notes using decision-tree-based support vector machines. Features are extracted from harmonics and residuals based on physical acoustics considerations and signal observations. We consider four distinct pedaling techniques on the sustain pedal (anticipatory full, anticipatory half, legato full, and legato half pedaling) and create a new isolated-note dataset consisting of different pitches and velocities for each pedaling technique plus notes played without pedal. Experiment shows the effectiveness of the designed features and the learned classifiers for discriminating pedaling techniques from the cross-validation trails.
Automatic detection of piano pedaling techniques is challenging as it is comprised of subtle nuances of piano timbres. In this paper we address this problem on single notes using decision-tree-based support vector machines. Features are extracted from harmonics and residuals based on physical acoustics considerations and signal observations. We consider four distinct pedaling techniques on the sustain pedal (anticipatory full, anticipatory half, legato full, and legato half pedaling) and create a new isolated-note dataset consisting of different pitches and velocities for each pedaling technique plus notes played without pedal. Experiment shows the effectiveness of the designed features and the learned classifiers for discriminating pedaling techniques from the cross-validation trails.
Authors:
Liang, Beici; Fazekas, György; Sandler, Mark B.
Affiliation:
Queen Mary University of London, London, UK
AES Convention:
143 (October 2017)
Paper Number:
9812
Publication Date:
October 8, 2017Import into BibTeX
Subject:
Signal Processing
Permalink:
http://www.aes.org/e-lib/browse.cfm?elib=19209