dc.contributor.author | Lordelo, C | |
dc.contributor.author | Benetos, E | |
dc.contributor.author | Dixon, S | |
dc.contributor.author | Ahlbäck, S | |
dc.contributor.editor | Lee, JH | |
dc.contributor.editor | Lerch, A | |
dc.contributor.editor | Duan, Z | |
dc.contributor.editor | Nam, J | |
dc.contributor.editor | Rao, P | |
dc.contributor.editor | Kranenburg, PV | |
dc.contributor.editor | Srinivasamurthy, A | |
dc.date.accessioned | 2024-07-09T10:30:58Z | |
dc.date.available | 2024-07-09T10:30:58Z | |
dc.date.issued | 2021 | |
dc.identifier.isbn | 978-1-7327299-0-2 | |
dc.identifier.uri | https://qmro.qmul.ac.uk/xmlui/handle/123456789/97927 | |
dc.description.abstract | This paper proposes a deep convolutional neural network
for performing note-level instrument assignment. Given a
polyphonic multi-instrumental music signal along with its
ground truth or predicted notes, the objective is to assign
an instrumental source for each note. This problem is addressed as a pitch-informed classification task where each
note is analysed individually. We also propose to utilise
several kernel shapes in the convolutional layers in order
to facilitate learning of timbre-discriminative feature maps.
Experiments on the MusicNet dataset using 7 instrument
classes show that our approach is able to achieve an average F-score of 0.904 when the original multi-pitch annotations are used as the pitch information for the system, and
that it also excels if the note information is provided using
third-party multi-pitch estimation algorithms. We also include ablation studies investigating the effects of the use of
multiple kernel shapes and comparing different input representations for the audio and the note-related information. | en_US |
dc.format.extent | 389 - 395 | |
dc.publisher | arXiv | en_US |
dc.title | Pitch-Informed Instrument Assignment using a Deep Convolutional Network with Multiple Kernel Shapes. | en_US |
dc.type | Conference Proceeding | en_US |
dc.rights.holder | © 2024 The Author(s) | |
pubs.notes | Not known | en_US |
pubs.publisher-url | http://www.informatik.uni-trier.de/~ley/db/conf/ismir/ismir2021.html | en_US |
rioxxterms.funder | Default funder | en_US |
rioxxterms.identifier.project | Default project | en_US |
rioxxterms.funder.project | b215eee3-195d-4c4f-a85d-169a4331c138 | en_US |