Show simple item record

dc.contributor.authorKirchhoff, H
dc.contributor.authorDixon, S
dc.contributor.authorKlapuri, A
dc.contributor.authorKlapuri, A
dc.date.accessioned2015-07-28T09:59:52Z
dc.date.available2015-07-28T09:59:52Z
dc.date.issued2013-10-18
dc.identifier.issn1520-6149
dc.identifier.urihttp://qmro.qmul.ac.uk/xmlui/handle/123456789/8031
dc.description.abstractFor a user-assisted music transcription system in which the user is asked to label some notes for each instrument in the recording, we investigate ways to limit the amount of information the user has to provide. Different methods are proposed and experimentally compared that enable the estimation of template spectra at pitch positions that have not been annotated by the user, in order to derive a full set of instrument templates that can be used within a non-negative matrix factorisation framework. A set of error metrics is presented that enables the evaluation of the NMF gain matrix. The results show that purely data-driven methods outperform more refined instrument models when the user annotates notes at many different pitches for each instrument. When notes are labelled at a smaller number of different pitches, the highest accuracies are obtained using pre-stored instrument templates that are adapted to the instruments in the mixture. © 2013 IEEE.
dc.format.extent26 - 30
dc.relation.isreplacedby123456789/11223
dc.relation.isreplacedbyhttp://qmro.qmul.ac.uk/xmlui/handle/123456789/11223
dc.titleMissing template estimation for user-assisted music transcription
dc.typeJournal Article
dc.identifier.doi10.1109/ICASSP.2013.6637602
dc.relation.isPartOfICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record