Show simple item record

dc.contributor.authorWANG, Cen_US
dc.contributor.authorBENETOS, Een_US
dc.contributor.authorMENG, Xen_US
dc.contributor.authorCHEW, Een_US
dc.contributor.authorInternational Society for Music Information Retrieval Conference Late-Breaking Demos Sessionen_US
dc.date.accessioned2018-10-02T09:43:25Z
dc.date.available2018-08-13en_US
dc.date.issued2018-09-23en_US
dc.date.submitted2018-09-29T18:15:49.356Z
dc.identifier.urihttp://qmro.qmul.ac.uk/xmlui/handle/123456789/45825
dc.description.abstractPlaying techniques such as ornamentations and articulation effects constitute important aspects of music performance. However, their computational analysis is still under-explored due to a lack of data and established methods. Focusing on the Chinese bamboo flute, we introduce a two-stage glissando detection system based on hidden Markov models (HMMs) with Gaussian mixtures. A rule-based segmentation process extracts glissando candidates that are consecutive note changes in the same direction. Glissandi are then identified by two HMMs (glissando and non-glissando). The study uses a newly created dataset of Chinese bamboo flute recordings. The results, based on both frame- and segment-based evaluation, achieve F-measures of 78% and 73% for ascending glissandi, and 65% and 72% for descending glissandi, respectively. The dataset and method can be used for performance analysis.en_US
dc.rightsCC BY 4.0
dc.titleTowards HMM-based glissando detection for recordings of Chinese bamboo fluteen_US
dc.typeConference Proceeding
dc.rights.holder© The Author(s) 2018
pubs.notesNo embargoen_US
pubs.publication-statusPublisheden_US
dcterms.dateAccepted2018-08-13en_US
qmul.funderA Machine Learning Framework for Audio Analysis and Retrieval::Royal Academy of Engineeringen_US


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record