Welcome to the UPF Digital Repository

Similarity of nearest-neighbor query results in deep latent spaces

Show simple item record

dc.contributor.author Tovstogan, Philip
dc.contributor.author Serra, Xavier
dc.contributor.author Bogdanov, Dmitry
dc.date.accessioned 2022-07-12T06:11:25Z
dc.date.available 2022-07-12T06:11:25Z
dc.date.issued 2022
dc.identifier.citation Tovstogan P, Serra X, Bogdanov D. Similarity of nearest-neighbor query results in deep latent spaces. In: Proceedings of the SMC 2022 Music technology and design; 2022 June 5-12; Saint-Étienne, France. Saint-Étienne: SMC; 2022. p. 287-94.
dc.identifier.uri http://hdl.handle.net/10230/53709
dc.description Comunicació presentada a: 19th Sound and Music Computing Conference, celebrat del 5 al 12 de juny de 2022 a Sant-Étienne
dc.description.abstract Music recommendation systems are commonly used for personalized recommendations. However, there are cases where due to privacy concerns or design decisions, there is no user information nor collaborative filtering data available. In those cases, it is possible to use content-based similarity spaces to retrieve the most similar tracks to be recommended based on the reference track. In this paper, we compare the latent spaces extracted from state-of-the-art autotagging models in terms of the similarity between lists of retrieved nearest neighbors. We additionally study item factors from collaborative-filtering data as a reference. We provide insights into how much the choice of the architecture, training dataset, or model layer (output vs. penultimate) as well as a projection of the latent space onto 2D changes the list of retrieved nearest neighbors. We release the dataset of 9 content-based and 3 collaborative-filtering latent representations of 29 275 tracks from Jamendo that we use for the evaluation. Moreover, we perform an online user experiment to compare the perceived track-to-track similarity of the selected evaluated latent spaces. The results show that content-based spaces show better results in our scenario, particularly embeddings from penultimate layers of auto-tagging architectures.
dc.description.sponsorship This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skøodowska-Curie grant agreement No. 765068.
dc.format.mimetype application/pdf
dc.language.iso eng
dc.publisher Sound and Music Computing
dc.relation.ispartof Proceedings of the SMC 2022 Music technology and design; 2022 June 5-12; Saint-Étienne, France. Saint-Étienne: SMC; 2022.
dc.rights © 2022 Philip Tovstogan et al. This is an open-access article distributed under the terms of theCreative Commons Attribution 3.0 Unported License, which permits unre-stricted use, distribution, and reproduction in any medium, provided the originalauthor and source are credite
dc.rights.uri https://creativecommons.org/licenses/by/3.0/
dc.title Similarity of nearest-neighbor query results in deep latent spaces
dc.type info:eu-repo/semantics/conferenceObject
dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/765068
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

Compliant to Partaking