Publication
Symbolic music generation conditioned on continuous-valued emotions
| dc.contributor.author | Sulun, Serkan | |
| dc.contributor.author | Davies, Matthew E. P. | |
| dc.contributor.author | Viana, Paula | |
| dc.date.accessioned | 2023-01-19T12:18:39Z | |
| dc.date.available | 2023-01-19T12:18:39Z | |
| dc.date.issued | 2022-04-22 | |
| dc.description.abstract | In this paper we present a new approach for the generation of multi-instrument symbolic music driven by musical emotion. The principal novelty of our approach centres on conditioning a state-of-the-art transformer based on continuous-valued valence and arousal labels. In addition, we provide a new large-scale dataset of symbolic music paired with emotion labels in terms of valence and arousal. We evaluate our approach in a quantitative manner in two ways, first by measuring its note prediction accuracy, and second via a regression task in the valence-arousal plane. Our results demonstrate that our proposed approaches outperform conditioning using control tokens which is representative of the current state of the art. | pt_PT |
| dc.description.sponsorship | ‘la Caixa’’ Foundation under Grant 100010434 and Grant LCF/BQ/DI19/1173003 - FCT—Foundation for Science and Technology, I.P., through the Project MERGE through the National Funds (PIDDAC) through the Portuguese State Budget under Grant PTDC/CCI-COM/3171/2021 - European Social Fund through the Regional Operational Program Centro 2020 Project CISUC under Grant UID/CEC/00326/2020 | pt_PT |
| dc.description.version | info:eu-repo/semantics/publishedVersion | pt_PT |
| dc.identifier.citation | S. Sulun, M. E. P. Davies and P. Viana, "Symbolic Music Generation Conditioned on Continuous-Valued Emotions," in IEEE Access, vol. 10, pp. 44617-44626, 2022, doi: 10.1109/ACCESS.2022.3169744. | pt_PT |
| dc.identifier.doi | 10.1109/ACCESS.2022.3169744 | pt_PT |
| dc.identifier.uri | http://hdl.handle.net/10400.22/21681 | |
| dc.language.iso | eng | pt_PT |
| dc.peerreviewed | yes | pt_PT |
| dc.publisher | IEEE | pt_PT |
| dc.relation | LCF/BQ/DI19/1173003 | pt_PT |
| dc.relation | Music Emotion Recognition - Next Generation | |
| dc.relation.publisherversion | https://ieeexplore.ieee.org/abstract/document/9762257 | pt_PT |
| dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ | pt_PT |
| dc.subject | Deep Learning | pt_PT |
| dc.subject | Symbolic Music Generation | pt_PT |
| dc.subject | Emotion-Based Music Generation | pt_PT |
| dc.subject | Transformers | pt_PT |
| dc.title | Symbolic music generation conditioned on continuous-valued emotions | pt_PT |
| dc.type | journal article | |
| dspace.entity.type | Publication | |
| oaire.awardTitle | Music Emotion Recognition - Next Generation | |
| oaire.awardURI | info:eu-repo/grantAgreement/FCT/3599-PPCDT/PTDC%2FCCI-COM%2F3171%2F2021/PT | |
| oaire.citation.endPage | 44626 | pt_PT |
| oaire.citation.startPage | 44617 | pt_PT |
| oaire.citation.title | IEEE Access | pt_PT |
| oaire.citation.volume | 10 | pt_PT |
| oaire.fundingStream | 3599-PPCDT | |
| person.familyName | Sülün | |
| person.familyName | Viana | |
| person.givenName | Serkan | |
| person.givenName | Paula | |
| person.identifier | FehjYXEAAAAJ | |
| person.identifier | 936138 | |
| person.identifier.ciencia-id | D015-A81C-37EE | |
| person.identifier.ciencia-id | EA17-B097-BD2E | |
| person.identifier.orcid | 0000-0003-1365-1884 | |
| person.identifier.orcid | 0000-0001-8447-2360 | |
| person.identifier.scopus-author-id | 7003678537 | |
| project.funder.identifier | http://doi.org/10.13039/501100001871 | |
| project.funder.name | Fundação para a Ciência e a Tecnologia | |
| rcaap.rights | openAccess | pt_PT |
| rcaap.type | article | pt_PT |
| relation.isAuthorOfPublication | d26a5b30-64a7-4e76-8ee3-cb770529cb1d | |
| relation.isAuthorOfPublication | 17ac1586-7589-4027-a541-3aea351fd6ae | |
| relation.isAuthorOfPublication.latestForDiscovery | d26a5b30-64a7-4e76-8ee3-cb770529cb1d | |
| relation.isProjectOfPublication | 9e030fe1-3608-4633-b1c8-fd92e82e1f36 | |
| relation.isProjectOfPublication.latestForDiscovery | 9e030fe1-3608-4633-b1c8-fd92e82e1f36 |