Welcome to the UPF Digital Repository

Score-informed syllable segmentation for Jingju a cappella singing voice with Mel-frequency intensity profiles

Show simple item record

dc.contributor.author Gong, Rong
dc.contributor.author Obin, Nicolas
dc.contributor.author Dzhambazov, Georgi Bogomilov
dc.contributor.author Serra, Xavier
dc.date.accessioned 2018-08-22T09:29:21Z
dc.date.available 2018-08-22T09:29:21Z
dc.date.issued 2017
dc.identifier.citation Gong R, Obin N, Dzhambazov G, Serra X. Score-informed syllable segmentation for Jingju a cappella singing voice with Mel-frequency intensity profiles. In: Barbancho I, Tardón LJ, Peinado A, editors. Proceedings of the 7th International Workshop on Folk Music Analysis; 2017 Jun 14-16; Málaga, Spain. Málaga: FMA; 2017. p. 107-13.
dc.identifier.isbn 978-84-697-2303-6
dc.identifier.uri http://hdl.handle.net/10230/35346
dc.description Comunicació presentada al International Workshop on Folk Music Analysis, celebrat del 14 al 16 de juny a Màlaga, Espanya.
dc.description.abstract This paper introduces a new unsupervised and score-informed method for the segmentation of singing voice into syllables. The main idea of the proposed method is to detect the syllable onset on a probability density function by incorporating a priori syllable duration derived from the score. Firstly, intensity profiles are used to exploit the characteristics of singing voice depending on the Mel-frequency regions. Then, the syllable onset probability density function is obtained by selecting candidates over the intensity profiles and weighted for the purpose of emphasizing the onset regions. Finally, the syllable duration distribution shaped by the score is incorporated into Viterbi decoding to determine the optimal sequence of onset time positions. The proposed method outperforms conventional methods for the segmentation of syllable on a jingju (also known as Peking or Beijing opera) a cappella dataset. An analysis is conducted on precision errors to provide direction for future improvement.
dc.description.sponsorship This work is partly supported by the European Research Council under the European Union’s Seventh Framework Program, as part of the CompMusic project (ERC grand agreement 267583).
dc.format.mimetype application/pdf
dc.language.iso eng
dc.publisher Folk Music Analysis
dc.relation.ispartof In: Barbancho I, Tardón LJ, Peinado A, editors. Proceedings of the 7th International Workshop on Folk Music Analysis; 2017 Jun 14-16; Málaga, Spain. Málaga: FMA; 2017.
dc.relation.isreferencedby http://doi.org/10.5281/zenodo.345490
dc.rights © Folk Music Analysis
dc.title Score-informed syllable segmentation for Jingju a cappella singing voice with Mel-frequency intensity profiles
dc.type info:eu-repo/semantics/conferenceObject
dc.relation.projectID info:eu-repo/grantAgreement/EC/FP7/267583
dc.rights.accessRights info:eu-repo/semantics/openAccess
dc.type.version info:eu-repo/semantics/publishedVersion

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account

Statistics

In collaboration with Compliant to Partaking