Show simple item record

dc.contributor.authorHartmann, Martin
dc.contributor.authorLartillot, Olivier
dc.contributor.authorToiviainen, Petri
dc.date.accessioned2017-07-11T06:57:57Z
dc.date.available2017-07-11T06:57:57Z
dc.date.issued2017
dc.identifier.citationHartmann, M., Lartillot, O., & Toiviainen, P. (2017). Musical Feature and Novelty Curve Characterizations as Predictors of Segmentation Accuracy. In T. Lokki, J. Pätynen, & V. Välimäki (Eds.), <em>SMC 2017 : Proceedings of the 14th Sound and Music Computing Conference 2017</em> (pp. 365-372). Helsinki, Finland: Aalto-yliopisto. Retrieved from <a href="http://smc2017.aalto.fi/media/materials/proceedings/SMC17_p365.pdf">http://smc2017.aalto.fi/media/materials/proceedings/SMC17_p365.pdf</a>
dc.identifier.otherTUTKAID_74411
dc.identifier.urihttps://jyx.jyu.fi/handle/123456789/54912
dc.description.abstractNovelty detection is a well-established method for analyzing the structure of music based on acoustic descriptors. Work on novelty-based segmentation prediction has mainly concentrated on enhancement of features and similarity matrices, novelty kernel computation and peak detection. Less attention, however, has been paid to characteristics of musical features and novelty curves, and their contribution to segmentation accuracy. This is particularly important as it can help unearth acoustic cues prompting perceptual segmentation and find new determinants of segmentation model performance. This study focused on spectral, rhythmic and harmonic prediction of perceptual segmentation density, which was obtained for six musical examples from 18 musician listeners via an annotation task. The proposed approach involved comparisons between perceptual segment density and novelty curves; in particular, we investigated possible predictors of segmentation accuracy based on musical features and novelty curves. For pitch and rhythm, we found positive correlates between segmentation accuracy and both local variability of musical features and mean distance between subsequent local maxima of novelty curves. According to the results, segmentation accuracy increases for stimuli with milder local changes and fewer novelty peaks. Implications regarding prediction of listeners’ segmentation are discussed in the light of theoretical postulates of perceptual organization.
dc.language.isoeng
dc.publisherAalto-yliopisto
dc.relation.ispartofSMC 2017 : Proceedings of the 14th Sound and Music Computing Conference 2017, ISBN 978-952-60-3729-5
dc.relation.ispartofseriesProceedings of the Sound and Music Computing Conferences;
dc.relation.urihttp://smc2017.aalto.fi/media/materials/proceedings/SMC17_p365.pdf
dc.subject.othermusic
dc.subject.othernotation (music)
dc.subject.otherpredictability
dc.subject.otherrhythm
dc.subject.otherkeys (tone systems)
dc.subject.othernovelty detection
dc.subject.othernovelty curves
dc.subject.othermusical features
dc.titleMusical Feature and Novelty Curve Characterizations as Predictors of Segmentation Accuracy
dc.typeconferenceObject
dc.identifier.urnURN:NBN:fi:jyu-201707103272
dc.contributor.laitosMusiikin, taiteen ja kulttuurin tutkimuksen laitosfi
dc.contributor.laitosDepartment of Music, Art and Culture Studiesen
dc.contributor.oppiaineMusic, Mind & Technology
dc.contributor.oppiaineMusiikkitiede
dc.type.urihttp://purl.org/eprint/type/ConferencePaper
dc.date.updated2017-07-10T09:15:05Z
dc.type.coarconference paper
dc.description.reviewstatuspeerReviewed
dc.format.pagerange365-372
dc.relation.issn2518-3672
dc.type.versionacceptedVersion
dc.rights.copyright© 2017 Martin Hartmann et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 Unported License.
dc.rights.accesslevelopenAccessfi
dc.rights.urlhttps://creativecommons.org/licenses/by/3.0/


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

© 2017 Martin Hartmann et al. This is an open-access article distributed
under the terms of the Creative Commons Attribution 3.0 Unported License.
Except where otherwise noted, this item's license is described as © 2017 Martin Hartmann et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 Unported License.