Afficher la notice abrégée

Evaluation of Real-Time Aliasing Reduction Methods in Neural Networks for Nonlinear Audio Effects Modelling

hal.structure.identifierUniversité de Bordeaux [UB]
hal.structure.identifierInstitut de Mathématiques de Bordeaux [IMB]
hal.structure.identifierOrosys
hal.structure.identifierMéthodes avancées d’apprentissage statistique et de contrôle [ASTRAL]
dc.contributor.authorVANHATALO, Tara
hal.structure.identifierUniversité de Bordeaux [UB]
hal.structure.identifierInstitut de Mathématiques de Bordeaux [IMB]
hal.structure.identifierMéthodes avancées d’apprentissage statistique et de contrôle [ASTRAL]
dc.contributor.authorLEGRAND, Pierrick
hal.structure.identifierStudio de Création et de Recherche en Informatique et Musique Électroacoustique [SCRIME]
hal.structure.identifierLaboratoire Bordelais de Recherche en Informatique [LaBRI]
dc.contributor.authorDESAINTE-CATHERINE, Myriam
hal.structure.identifierImage et Son
hal.structure.identifierLaboratoire Bordelais de Recherche en Informatique [LaBRI]
dc.contributor.authorHANNA, Pierre
hal.structure.identifierOrosys
dc.contributor.authorPILLE, Guillaume
dc.date.issued2023-10-09
dc.identifier.issn0004-7554
dc.description.abstractEnNeural networks have seen increased popularity in recent years for nonlinear audio effects modelling. Such a task requires sampling and creates high frequency harmonics that can quickly surpass the Nyquist rate, creating aliasing in the baseband. In this work, we study the impact of processing audio with neural networks and the potential aliasing these highly nonlinear algorithms can incur or aggravate. Namely, we evaluate the performance of a number of anti-aliasing methods for use in real-time. Notably, one method of anti-aliasing capable of real-time performance was identified: forced sparsity through network pruning.
dc.language.isoen
dc.publisherAudio Engineering Society
dc.rights.urihttp://creativecommons.org/licenses/by/
dc.subject.enAliasing reduction
dc.subject.enneural networks
dc.subject.ennonlinear audio effects modelling
dc.subject.enreal-time
dc.title.enEvaluation of Real-Time Aliasing Reduction Methods in Neural Networks for Nonlinear Audio Effects Modelling
dc.typeArticle de revue
dc.identifier.doi10.17743/jaes.2022.0122
dc.subject.halInformatique [cs]
dc.subject.halInformatique [cs]
dc.subject.halMathématiques [math]
dc.subject.halScience non linéaire [physics]
bordeaux.journalJournal of the Audio Engineering Society
bordeaux.peerReviewedoui
hal.identifierhal-04235385
hal.version1
hal.popularnon
hal.audienceInternationale
hal.origin.linkhttps://hal.archives-ouvertes.fr//hal-04235385v1
bordeaux.COinSctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.jtitle=Journal%20of%20the%20Audio%20Engineering%20Society&rft.date=2023-10-09&rft.eissn=0004-7554&rft.issn=0004-7554&rft.au=VANHATALO,%20Tara&LEGRAND,%20Pierrick&DESAINTE-CATHERINE,%20Myriam&HANNA,%20Pierre&PILLE,%20Guillaume&rft.genre=article


Fichier(s) constituant ce document

FichiersTailleFormatVue

Il n'y a pas de fichiers associés à ce document.

Ce document figure dans la(les) collection(s) suivante(s)

Afficher la notice abrégée