dc.contributor.author | Fano Yela, D | en_US |
dc.contributor.author | Stowell, D | en_US |
dc.contributor.author | Sandler, M | en_US |
dc.contributor.author | LVA-ICA | en_US |
dc.date.accessioned | 2018-08-07T10:09:28Z | |
dc.date.available | 2018-03-19 | en_US |
dc.date.issued | 2018-06-06 | en_US |
dc.date.submitted | 2018-08-01T15:28:25.554Z | |
dc.identifier.isbn | 9783319937632 | en_US |
dc.identifier.issn | 0302-9743 | en_US |
dc.identifier.uri | http://qmro.qmul.ac.uk/xmlui/handle/123456789/43083 | |
dc.description | LVA-ICA 2018 - Feedback always welcome | en_US |
dc.description.abstract | Kernel Additive Modelling (KAM) is a framework for source separation aiming to explicitly model inherent properties of sound sources to help with their identification and separation. KAM separates a given source by applying robust statistics on the selection of time-frequency bins obtained through a source-specific kernel, typically the k-NN function. Even though the parameter k appears to be key for a successful separation, little discussion on its influence or optimisation can be found in the literature. Here we propose a novel method, based on graph theory statistics, to automatically optimise k in a vocal separation task. We introduce the k-NN hubness as an indicator to find a tailored k at a low computational cost. Subsequently, we evaluate our method in comparison to the common approach to choose k. We further discuss the influence and importance of this parameter with illuminating results. | en_US |
dc.format.extent | 280 - 289 | en_US |
dc.rights | This is a pre-copyedited, author-produced version of an article accepted for publication in International Conference on Latent Variable Analysis and Signal Separation following peer review. The version of record is available https://link.springer.com/chapter/10.1007%2F978-3-319-93764-9_27 | |
dc.title | Does K matter? k-NN hubness analysis for kernel additive modelling vocal separation | en_US |
dc.type | Conference Proceeding | |
dc.rights.holder | © Springer International Publishing AG, part of Springer Nature 2018 | |
dc.identifier.doi | 10.1007/978-3-319-93764-9_27 | en_US |
pubs.notes | No embargo | en_US |
pubs.publication-status | Published | en_US |
pubs.volume | 10891 LNCS | en_US |
dcterms.dateAccepted | 2018-03-19 | en_US |
qmul.funder | Structured machine listening for soundscapes with multiple birds::EPSRC | en_US |
qmul.funder | Structured machine listening for soundscapes with multiple birds::EPSRC | en_US |