dc.contributor.author | Valero-Mas, JJ | en_US |
dc.contributor.author | Benetos, E | en_US |
dc.contributor.author | Iñesta, JM | en_US |
dc.contributor.author | 9th International Workshop on Machine Learning and Music | en_US |
dc.date.accessioned | 2016-09-05T13:03:08Z | |
dc.date.available | 2016-07-30 | en_US |
dc.date.issued | 2016-09-23 | en_US |
dc.date.submitted | 2016-08-15T19:37:24.176Z | |
dc.identifier.uri | http://qmro.qmul.ac.uk/xmlui/handle/123456789/14957 | |
dc.description.abstract | Note tracking constitutes a key process in Automatic Music Transcription as it derives a note-level transcription from a frame-based pitch activation representation. While this stage is commonly performed using a set of hand-crafted rules, this work presents an approach based on supervised classification which automatically infers these policies. An initial frame-level estimation provides the necessary information for segmenting each pitch band in single instances which are later classified as active or non-active note events. Preliminary results using classic classification strategies on a subset of the MAPS piano dataset report an improvement of up to a 15% when compared to the baseline considered for both frame-level and note-level assessment. | en_US |
dc.format.extent | 61 - 65 (5) | en_US |
dc.title | Classification-based Note Tracking for Automatic Music Transcription | en_US |
dc.type | Conference Proceeding | |
pubs.notes | Not known | en_US |
pubs.publication-status | Published | en_US |
pubs.publisher-url | https://sites.google.com/site/musicmachinelearning16/ | en_US |
dcterms.dateAccepted | 2016-07-30 | en_US |
qmul.funder | A Machine Learning Framework for Audio Analysis and Retrieval::Royal Academy of Engineering | en_US |