Show simple item record

dc.contributor.authorBenetos, Een_US
dc.contributor.authorBadeau, Ren_US
dc.contributor.authorWeyde, Ten_US
dc.contributor.authorRichard, Gen_US
dc.contributor.author15th International Society for Music Information Retrieval Conference (ISMIR)en_US
dc.contributor.editorWang, H-Men_US
dc.contributor.editorYang, Y-Hen_US
dc.contributor.editorLee, JHen_US
dc.date.accessioned2015-11-25T10:54:28Z
dc.date.issued2014-10-27en_US
dc.identifier.urihttp://qmro.qmul.ac.uk/xmlui/handle/123456789/9414
dc.descriptionpublicationstatus: published
dc.descriptionpublicationstatus: publisheden_US
dc.descriptionpublicationstatus: publisheden_US
dc.description.abstractIn this work, we propose a system for automatic music transcription which adapts dictionary templates so that they closely match the spectral shape of the instrument sources present in each recording. Current dictionary-based automatic transcription systems keep the input dictionary fixed, thus the spectral shape of the dictionary components might not match the shape of the test instrument sources. By performing a conservative transcription pre-processing step, the spectral shape of detected notes can be extracted and utilized in order to adapt the template dictionary. We propose two variants for adaptive transcription, namely for single-instrument transcription and for multiple-instrument transcription. Experiments are carried out using the MAPS and Bach10 databases. Results in terms of multi-pitch detection and instrument assignment show that there is a clear and consistent improvement when adapting the dictionary in contrast with keeping the dictionary fixed.en_US
dc.format.extent175 - 180en_US
dc.language.isoenen_US
dc.rightshttp://dblp.uni-trier.de/db/conf/ismir/ismir2014.html
dc.titleTemplate Adaptation for Improving Automatic Music Transcriptionen_US
dc.typeConference Proceeding
pubs.author-urlhttp://www.terasoft.com.tw/conf/ismir2014//proceedings/T032_235_Paper.pdfen_US
pubs.notesNo embargoen_US
pubs.organisational-group/Queen Mary University of London
pubs.organisational-group/Queen Mary University of London/Faculty of Science & Engineering
pubs.organisational-group/Queen Mary University of London/Faculty of Science & Engineering/Electronic Engineering and Computer Science - Staff
pubs.organisational-group/Queen Mary University of London/REF
pubs.organisational-group/Queen Mary University of London/REF/REF - UoA 11
pubs.publisher-urlhttp://www.city.ac.uk/people/academics/emmanouil-benetosen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record