Welcome to the UPF Digital Repository

Data-driven harmonic filters for audio representation learning

Show simple item record

dc.contributor.author Won, Minz
dc.contributor.author Chun, Sanghyuk
dc.contributor.author Nieto Caballero, Oriol
dc.date.accessioned 2020-04-20T08:26:16Z
dc.date.issued 2020
dc.identifier.citation Won M, Chun S, Nieto O, Serra X. Data-driven harmonic filters for audio representation learning. In: 2020 IEEE InternationalConference on Acoustics, Speech,and Signal Processing Proceedings; 2020 May 4-8; Barcelona, Spain. [New York]: IEEE; 2020. p. 536-40. DOI: 10.1109/ICASSP40776.2020.9053669
dc.identifier.isbn 978-1-5090-6631-5
dc.identifier.issn 2379-190X
dc.identifier.uri http://hdl.handle.net/10230/44278
dc.description Comunicació presentada a: ICASSP 2020 IEEE InternationalConference on Acoustics, Speech,and Signal Processing, celebrat en línia del 4 al 8 de maig de 2020.
dc.description.abstract We introduce a trainable front-end module for audio repre- sentation learning that exploits the inherent harmonic struc- ture of audio signals. The proposed architecture, composed of a set of filters, compels the subsequent network to cap- ture harmonic relations while preserving spectro-temporal lo- cality. Since the harmonic structure is known to have a key role in human auditory perception, one can expect these har- monic filters to yield more efficient audio representations. Ex- perimental results show that a simple convolutional neural network back-end with the proposed front-end outperforms state-of-the-art baseline methods in automatic music tagging, keyword spotting, and sound event tagging tasks.
dc.description.sponsorship This work was funded by the predoctoral grant MDM-2015- 0502-17-2 from the Spanish Ministry of Economy and Com- petitiveness linked to the Maria de Maeztu Units of Excel- lence Programme (MDM-2015-0502).
dc.format.mimetype application/pdf
dc.language.iso eng
dc.publisher Institute of Electrical and Electronics Engineers (IEEE)
dc.relation.ispartof 2020 IEEE InternationalConference on Acoustics, Speech,and Signal Processing Proceedings; 2020 May 4-8; Barcelona, Spain. [New York]: IEEE; 2020. p. 536-40.
dc.rights © 2020 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/ICASSP40776.2020.9053669
dc.title Data-driven harmonic filters for audio representation learning
dc.type info:eu-repo/semantics/conferenceObject
dc.identifier.doi http://dx.doi.org/10.1109/ICASSP40776.2020.9053669
dc.subject.keyword Harmonic filters
dc.subject.keyword Audio representation learning
dc.subject.keyword Deep learning
dc.rights.accessRights info:eu-repo/semantics/embargoedAccess
dc.type.version info:eu-repo/semantics/acceptedVersion
dc.embargo.liftdate 2022-04-09
dc.date.embargoEnd info:eu-repo/date/embargoEnd/2022-04-09

Blocked

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account

Statistics

Compliant to Partaking