Show simple item record

dc.contributor.authorPauwels, Jen_US
dc.contributor.authorO hanlon, Ken_US
dc.contributor.authorFazekas, Gen_US
dc.contributor.authorSandler, Men_US
dc.date.accessioned2017-12-15T11:13:52Z
dc.date.issued2017en_US
dc.date.submitted2017-12-07T17:57:10.077Z
dc.identifier.urihttp://qmro.qmul.ac.uk/xmlui/handle/123456789/30483
dc.descriptiondate-added: 2017-12-22 14:56:50 +0000 date-modified: 2017-12-22 15:05:47 +0000 keywords: music labelling, chord and key recognition, probabilistic models, confidence measure, usability, channel separation from stereo signals, Audio Commons local-url: https://qmro.qmul.ac.uk/xmlui/handle/123456789/30483 bdsk-url-1: https://ismir2017.smcnus.org/wp-content/uploads/2017/10/195_Paper.pdfen_US
dc.descriptiondate-added: 2017-12-22 14:56:50 +0000 date-modified: 2017-12-22 15:05:47 +0000 keywords: music labelling, chord and key recognition, probabilistic models, confidence measure, usability, channel separation from stereo signals, Audio Commons local-url: https://qmro.qmul.ac.uk/xmlui/handle/123456789/30483 bdsk-url-1: https://ismir2017.smcnus.org/wp-content/uploads/2017/10/195_Paper.pdfen_US
dc.description.abstractInspired by previous work on confidence measures for tempo estimation in loops, we explore ways to add confidence measures to other music labelling tasks. We start by reflecting on the reasons why the work on loops was successful and argue that it is an example of the ideal scenario in which it is possible to define a confidence measure independently of the estimation algorithm. This requires additional domain knowledge not used by the estimation algorithm, which is rarely available. Therefore we move our focus to defining confidence measures for hidden Markov models, a technique used in multiple music information retrieval systems and beyond. We propose two measures that are oblivious to the specific labelling task, trading off performance for computational requirements. They are experimentally validated by means of a chord estimation task. Finally, we have a look at alternative uses of confidence measures, besides those applications that require a high precision rather than a high recall, such as most query retrievals.en_US
dc.format.extent279 - 279en_US
dc.rightsLicensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0). Attribution: Johan Pauwels, Ken O’Hanlon, György Fazekas, Mark B. Sandler. “Confidence measures and their applications in music labelling systems based on hidden Markov models”, 18th International Society for Music Information Retrieval Conference, Suzhou, China, 2017.
dc.titleConfidence Measures and Their Applications in Music Labelling Systems Based on Hidden Markov Modelsen_US
dc.typeConference Proceeding
dc.rights.holder© 2017 Johan Pauwels, Ken O’Hanlon, György Fazekas, Mark B. Sandler.
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-urlhttps://ismir2017.smcnus.org/wp-content/uploads/2017/10/195_Paper.pdfen_US
qmul.funderFusing Semantic and Audio Technologies for Intelligent Music Production and Consumption::Engineering and Physical Sciences Research Councilen_US
qmul.funderFusing Semantic and Audio Technologies for Intelligent Music Production and Consumption::Engineering and Physical Sciences Research Councilen_US


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record