Transfer learning of artist group factors to musical genre classification

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Kim, Jaehunca
• dc.contributor.author Won, Minzca
• dc.contributor.author Serra, Xavierca
• dc.contributor.author Liem, Cynthia C. S.ca
• dc.date.accessioned 2018-05-08T11:13:26Z
• dc.date.available 2018-05-08T11:13:26Z
• dc.date.issued 2018
• dc.description Comunicació presentada a la World Wide Web Conference WWW2018, celebrada els dies 23 a 27 d'abril de 2018 a Lyon, França.
• dc.description.abstract The automated recognition of music genres from audio information is a challenging problem, as genre labels are subjective and noisy. Artist labels are less subjective and less noisy, while certain artists may relate more strongly to certain genres. At the same time, at prediction time, it is not guaranteed that artist labels are available for a given audio segment. Therefore, in this work, we propose to apply the transfer learning framework, learning artist-related information which will be used at inference time for genre classification. We consider different types of artist-related information, expressed through artist group factors, which will allow for more efficient learning and stronger robustness to potential label noise. Furthermore, we investigate how to achieve the highest validation accuracy on the given FMA dataset, by experimenting with various kinds of transfer methods, including single-task transfer, multi-task transfer and finally multi-task learning.en
• dc.description.sponsorship This work was carried out on the Dutch national e-infrastructure with the support of SURF Cooperative. And this work is partially supported by the Maria de Maeztu Programme (MDM-2015-0502). We further acknowledge the computing support of Kakao Corporation.
• dc.format.mimetype application/pdf
• dc.identifier.citation Kim J, Won M, Serra X, Liem CCS. Transfer learning of artist group factors to musical genre classification. In: Companion of The World Wide Web Conference WWW2018; 2018 Apr 23-27; Lyon, France. Geneva (Switzerland): ACM; 2018. p. 1929-34. DOI: 10.1145/3184558.3191823
• dc.identifier.doi http://dx.doi.org/10.1145/3184558.3191823
• dc.identifier.uri http://hdl.handle.net/10230/34581
• dc.language.iso eng
• dc.publisher ACM Association for Computer Machineryca
• dc.relation.ispartof Companion of The World Wide Web Conference WWW2018; 2018 Apr 23-27; Lyon, France. Geneva (Switzerland): ACM; 2018. p. 1929-34.
• dc.rights © 2018 IW3C2 (International World Wide Web Conference Committee), published under Creative Commons CC BY 4.0 License.
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.rights.uri http://creativecommons.org/licenses/by/4.0/
• dc.subject.keyword Music information retrievalen
• dc.subject.keyword Multi-task learningen
• dc.subject.keyword Transfer learningen
• dc.subject.keyword Neural networken
• dc.title Transfer learning of artist group factors to musical genre classificationca
• dc.type info:eu-repo/semantics/conferenceObject
• dc.type.version info:eu-repo/semantics/publishedVersion