Randomly weighted CNNs for (music) audio classification

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Pons Puig, Jordi
• dc.contributor.author Serra, Xavier
• dc.date.accessioned 2019-10-31T11:13:04Z
• dc.date.available 2019-10-31T11:13:04Z
• dc.date.issued 2018
• 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 The computer vision literature shows that randomly weighted neural networks perform reasonably as feature extractors. Following this idea, we study how non-trained (randomly weighted) convolutional neural networks perform as feature extractors for (music) audio classification tasks. We use features extracted from the embeddings of deep architectures as input to a classifier - with the goal to compare classification accuracies when using different randomly weighted architectures. By following this methodology, we run a comprehensive evaluation of the current architectures for audio classification, and provide evidence that the architectures alone are an important piece for resolving (music) audio problems using deep neural networks.
• dc.description.sponsorship This work is supported by the Maria de Maeztu Programme (MDM-2015-0502), and we are grateful for the GPUs donated by NVidia.
• dc.format.mimetype application/pdf
• dc.identifier.citation Pons J, Serra X. Randomly weighted CNNs for (music) audio classification. 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. 336-40. DOI: 10.1109/ICASSP.2019.8682912
• dc.identifier.doi http://dx.doi.org/10.1109/ICASSP.2019.8682912
• dc.identifier.isbn 978-1-4799-8131-1
• dc.identifier.issn 2379-190X
• dc.identifier.uri http://hdl.handle.net/10230/42575
• dc.language.iso eng
• dc.publisher Institute of Electrical and Electronics Engineers (IEEE)
• dc.relation.ispartof 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.
• dc.rights © Jordi Pons, Xavier Serra. Licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0). Attribution: Jordi Pons, Xavier Serra. “Randomly weighted CNNs for (music) audio classification
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.rights.uri https://creativecommons.org/licenses/by/4.0/
• dc.subject.keyword Random
• dc.subject.keyword Neural networks
• dc.subject.keyword Audio
• dc.subject.keyword ELM
• dc.subject.keyword SVM
• dc.title Randomly weighted CNNs for (music) audio classification
• dc.type info:eu-repo/semantics/conferenceObject
• dc.type.version info:eu-repo/semantics/publishedVersion