Data augmentation for deep learning source separation of HipHop songs

Mostra el registre complet Registre parcial de l'ítem

  • dc.contributor.author Martel Baro, Héctorca
  • dc.contributor.author Miron, Mariusca
  • dc.date.accessioned 2017-10-11T17:18:45Z
  • dc.date.available 2017-10-11T17:18:45Z
  • dc.date.issued 2017
  • dc.description Comunicació presentada a: 10th International Workshop on Machine Learning and Music, celebrat el 6 d'octbure de 2017 a Barcelona.ca
  • dc.description.abstract Training deep learning source separation methods involves computationally intensive procedures relying on large multi-track datasets. In this paper we use data augmentation to improve hip hop source sepa- ration using small training datasets. We analyze different training strate- gies and data augmentation techniques with respect to their generaliza- tion capabilities. Moreover, we propose a hip hop multi-track dataset and we implemented a web demo to demonstrate our use scenario. The evaluation is done on a part of the dataset and hip-hop songs from an external dataset.en
  • dc.format.mimetype application/pdf
  • dc.identifier.citation Martel H, Miron M. Data augmentation for deep learning source separation of HipHop songs. Paper presented at: 10th International Workshop on Machine Learning and Music; 2017 Oct 6; Barcelona, Spain.
  • dc.identifier.uri http://hdl.handle.net/10230/32930
  • dc.language.iso eng
  • dc.relation.projectID info:eu-repo/grantAgreement/ES/1PE/TIN2015-70816-R
  • dc.rights.accessRights info:eu-repo/semantics/openAccess
  • dc.subject.other Music source separationen
  • dc.subject.other Deep learningen
  • dc.subject.other Hip Hopen
  • dc.title Data augmentation for deep learning source separation of HipHop songsca
  • dc.type info:eu-repo/semantics/conferenceObject
  • dc.type.version info:eu-repo/semantics/acceptedVersion