Predicting dynamics in violin pieces with features from melodic motifs

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Muneratti Ortega, Fábio José
• dc.contributor.author Pérez Carrillo, Alfonso Antonio, 1977-
• dc.contributor.author Ramírez, Rafael,1966-
• dc.date.accessioned 2021-01-29T07:31:10Z
• dc.date.available 2021-01-29T07:31:10Z
• dc.date.issued 2019
• dc.description Comunicació presentada al Joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2019), celebrat del 16 al 20 de setembre de 2019 a Würzburg, Alemanya.
• dc.description.abstract We present a machine–learning model for predicting the performance dynamics in melodic motifs from classical pieces based on musically–meaningful features calculated from score–like symbolic representation. This model is designed to be capable of providing expressive directions to musicians within tools for expressive performance practice, and for that reason, in contrast with previous research, all modeling is done on a phrase level rather than note level. Results show the model is powerful but struggles with the generalization of predictions. The robustness of the chosen summarized representation of dynamics makes its application possible even in cases of low accuracy.
• dc.format.mimetype application/pdf
• dc.identifier.citation Muneratti Ortega FJ, Perez-Carrillo A, Ramírez R. Predicting dynamics in violin pieces with features from melodic motifs. In: Cellier P, Driessens, editors. Machine Learning and Knowledge Discovery in Databases. Joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2019); 2019 Sep 16-20; Würzburg, Germany. Cham: Springer; 2019. p. 517-523. DOI: 10.1007/978-3-030-43887-6_46
• dc.identifier.doi http://dx.doi.org/10.1007/978-3-030-43887-6_46
• dc.identifier.uri http://hdl.handle.net/10230/46292
• dc.language.iso eng
• dc.publisher Springer
• dc.relation.ispartof Cellier P, Driessens, editors. Machine Learning and Knowledge Discovery in Databases. Joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2019); 2019 Sep 16-20; Würzburg, Germany. Cham: Springer; 2019. p. 517-523
• dc.rights © Springer The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-030-43887-6_46
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.subject.keyword Expressive music performanceen
• dc.subject.keyword Machine learningen
• dc.subject.keyword Violinen
• dc.title Predicting dynamics in violin pieces with features from melodic motifsen
• dc.type info:eu-repo/semantics/conferenceObject
• dc.type.version info:eu-repo/semantics/acceptedVersion