Show simple item record

dc.contributor.authorSTOLLER, Den_US
dc.contributor.authorDixon, Sen_US
dc.contributor.author17th International Society for Music Information Retrieval Conference (ISMIR 2016)en_US
dc.date.accessioned2016-07-14T14:28:12Z
dc.date.available2016-05-13en_US
dc.date.submitted2016-07-07T11:09:45.775Z
dc.identifier.urihttp://qmro.qmul.ac.uk/xmlui/handle/123456789/13500
dc.description.abstractPhonation mode is an expressive aspect of the singing voice and can be described using the four categories neutral, breathy, pressed and flow. Previous attempts at automatically classifying the phonation mode on a dataset containing vowels sung by a female professional have been lacking in accuracy or have not sufficiently investigated the characteristic features of the different phonation modes which enable successful classification. In this paper, we extract a large range of features from this dataset, including specialised descriptors of pressedness and breathiness, to analyse their explanatory power and robustness against changes of pitch and vowel. We train and optimise a feed-forward neural network (NN) with one hidden layer on all features using cross validation to achieve a mean F-measure above 0.85 and an improved performance compared to previous work. Applying feature selection based on mutual information and retaining the nine highest ranked features as input to a NN results in a mean F-measure of 0.78, demonstrating the suitability of these features to discriminate between phonation modes. Training and pruning a decision tree yields a simple rule set based only on cepstral peak prominence (CPP), temporal flatness and average energy that correctly categorises 78% of the recordings.en_US
dc.rightshttp://wp.nyu.edu/ismir2016/
dc.titleAnalysis and classification of phonation modes in singingen_US
dc.typeConference Proceeding
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 - Computer Science - Research Students
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/Faculty Reporting - Research Students
pubs.organisational-group/Queen Mary University of London/Faculty Reporting - Research Students/Faculty of Science & Engineering PGRs
pubs.publication-statusAccepteden_US
dcterms.dateAccepted2016-05-13en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record