Search result clustering in collaborative sound collections

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Favory, Xavier
• dc.contributor.author Font Corbera, Frederic
• dc.contributor.author Serra, Xavier
• dc.date.accessioned 2025-05-28T06:05:14Z
• dc.date.available 2025-05-28T06:05:14Z
• dc.date.issued 2020
• dc.description.abstract Estimating music piece difficulty is important for organizing educational music collections. This process could be partially automatized to facilitate the educator’s role. Nevertheless, the decisions performed by prevalent deeplearning models are hardly understandable, which may impair the acceptance of such a technology in music education curricula. Our work employs explainable descriptors for difficulty estimation in symbolic music representations. Furthermore, through a novel parameter-efficient white-box model, we outperform previous efforts while delivering interpretable results. These comprehensible outcomes emulate the functionality of a rubric, a tool widely used in music education. Our approach, evaluated in piano repertoire categorized in 9 classes, achieved 41.4% accuracy independently, with a mean squared error (MSE) of 1.7, showing precise difficulty estimation. Through our baseline, we illustrate how building on top of past research can offer alternatives for music difficulty assessment which are explainable and interpretable. With this, we aim to promote a more effective communication between the Music Information Retrieval (MIR) community and the music education one.
• dc.format.mimetype application/pdf
• dc.identifier.citation Favory X, Font F, Serra X. Search result clustering in collaborative sound collections. In: Proceedings of the 2020 International Conference on Multimedia Retrieval (ICMR’20); 2020 June 8-11; Dublin, Ireland. New York (NY): ACM; 2020. p. 207-14. DOI: 10.1145/3372278.3390691
• dc.identifier.doi https://www.doi.org/10.1145/3372278.3390691
• dc.identifier.uri http://hdl.handle.net/10230/70538
• dc.language.iso eng
• dc.publisher ACM Association for Computer Machinery
• dc.rights © 2020 Association for Computing Machinery © P. Ramoneda, V. Eremenko, A. D’Hooge, E. Parada-Cabaleiro, X. Serra. Licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0). Attribution: P. Ramoneda, V. Eremenko, A. D’Hooge, E. Parada-Cabaleiro, X. Serra, “Towards Explainable and Interpretable Musical Difficulty Estimation: A parameter-efficient approach”, in Proc. of the 25th Int. Society for Music Information Retrieval Conf., San Francisco, USA, 2024.
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.rights.uri http://creativecommons.org/licenses/by/4.0
• dc.subject.keyword Unsupervised learning and clustering
• dc.subject.keyword Data structures
• dc.subject.keyword Algorithms for data management
• dc.subject.keyword Clustering
• dc.subject.keyword Multimedia databases
• dc.subject.keyword Content analysis
• dc.subject.keyword Cluster analysis
• dc.title Search result clustering in collaborative sound collections
• dc.type info:eu-repo/semantics/conferenceObject
• dc.type.version info:eu-repo/semantics/acceptedVersion