Welcome to the UPF Digital Repository

End-to-end sound source separation conditioned on instrument labels

Show simple item record

dc.contributor.author Slizovskaia, Olga
dc.contributor.author Kim, Leo
dc.contributor.author Haro Ortega, Gloria
dc.contributor.author Gómez Gutiérrez, Emilia, 1975-
dc.date.accessioned 2019-05-22T08:05:00Z
dc.date.issued 2019
dc.identifier.citation Slizovskaia O, Kim L, Haro G, Gomez E. End-to-end sound source separation conditioned on instrument labels. In: 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP); 2019 May 12-17; Brighton, United Kingdom. New Jersey: Institute of Electrical and Electronics Engineers; 2019. p. 306-10. DOI: 10.1109/ICASSP.2019.8683800
dc.identifier.issn 2379-190X
dc.identifier.uri http://hdl.handle.net/10230/37258
dc.description Comunicació presentada a: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing celebrat de 12 al 17 de maig de 2019 a Brighton, Regne Unit.
dc.description.abstract Can we perform an end-to-end music source separation with a variable number of sources using a deep learning model? This paper presents an extension of the Wave-UNet [1] model which allows end-to-end monaural source separation with a non-fixed number of sources. Furthermore, we propose multiplicative conditioning with instrument labels at the bottleneck of the Wave-U-Net and show its effect on the separation results. This approach can be further extended to other types of conditioning such as audio-visual source separation and score-informed source separation.
dc.description.sponsorship This work has received funding from the Maria de Maeztu Programme (MDM-2015-0502), ERC Innovation Programme (grant 770376, TROMPA), and MINECO/FEDER UE project (TIN2015-70410-C2-1-R).
dc.format.mimetype application/pdf
dc.language.iso eng
dc.publisher Institute of Electrical and Electronics Engineers (IEEE)
dc.rights © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. http://dx.doi.org/10.1109/ICASSP.2019.8683800
dc.title End-to-end sound source separation conditioned on instrument labels
dc.type info:eu-repo/semantics/conferenceObject
dc.subject.keyword Sound source separation
dc.subject.keyword End-to-end deep learning
dc.subject.keyword Wave-U-Net
dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/770376
dc.relation.projectID info:eu-repo/grantAgreement/ES/1PE/TIN2015-70410-C2-1-R
dc.rights.accessRights info:eu-repo/semantics/embargoedAccess
dc.type.version info:eu-repo/semantics/acceptedVersion
dc.embargo.liftdate 2019-10-17
dc.date.embargoEnd info:eu-repo/date/embargoEnd/2019-10-17


This item appears in the following Collection(s)

Show simple item record

Search DSpace

Advanced Search


My Account


Compliant to Partaking