Repository logo
 
Publication

Percussion and Instrumentation in Music Emotion Recognition: a Feature Engineering Approach

2025Journal Open access
Simple item page
dc.contributor.authorRedinho, Hugo
dc.contributor.authorLima Louro, Pedro Miguel
dc.contributor.authorSantos, André C.
dc.contributor.authorMalheiro, Ricardo
dc.contributor.authorPinto de Carvalho e Paiva, Rui Pedro
dc.contributor.authorPanda, Renato
dc.date.accessioned2025-11-29T11:06:06Z
dc.date.available2025-11-29T11:06:06Z
dc.date.issued2025
dc.description.abstractWe propose a new set of features for audio-based Music Emotion Recognition (MER) that are related to percussion and individual instrument information. One limitation of current feature engineering approaches in MER is that they primarily focus on melodic elements. However, the percussive elements and instrumentation are also essential for conveying and recognizing emotions in music. Our approach leverages the Demucs framework for music source separation (which enables drum channel separation) and the MT3 framework for automatic music transcription and instrument recognition. Building on the results of these frameworks, we created a new set of features that primarily capture information about musical texture, rhythm, dynamics, expressivity, tone color, and musical form. To validate our work, we utilized the MERGE dataset, which comprises over 3000 30-second audio clips annotated with Russell's emotion quadrants. To evaluate the impact of the new features, we compared classification results with those obtained using current state-of-the-art features, demonstrating statistically significant improvements in F1 score (from 71.1\% to 74.2\%). Moreover, the novel features helped to reduce the confusion between quadrants 3 and 4 (a common difficulty in MER models). The most significant finding of the present study is the impact of separately analyzing the drum channel, whose features proved particularly relevant.eng
dc.identifier.issn1949-3045
dc.identifier.urihttp://hdl.handle.net/10400.26/60133
dc.language.isoeng
dc.peerreviewedyes
dc.publisherIEEE
dc.relationMusic Emotion Recognition - Next Generation
dc.rights.uriN/A
dc.titlePercussion and Instrumentation in Music Emotion Recognition: a Feature Engineering Approacheng
dc.typejournal
dcterms.referenceshttps://zenodo.org/records/13939205
dspace.entity.typePublication
oaire.awardTitleMusic Emotion Recognition - Next Generation
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/3599-PPCDT/PTDC%2FCCI-COM%2F3171%2F2021/PT
oaire.citation.titleIEEE Transactions on Affective Computing
oaire.fundingStream3599-PPCDT
oaire.versionhttp://purl.org/coar/version/c_71e4c1898caa6e32
person.familyNameLima Louro
person.familyNamePinto de Carvalho e Paiva
person.familyNamePanda
person.givenNamePedro Miguel
person.givenNameRui Pedro
person.givenNameRenato
person.identifierWT5afVUAAAAJ
person.identifier.ciencia-idC315-8AA7-2C25
person.identifier.ciencia-idAA16-002F-5AE3
person.identifier.ciencia-id661A-31CC-8D19
person.identifier.orcid0000-0003-3201-6990
person.identifier.orcid0000-0003-3215-3960
person.identifier.orcid0000-0003-2539-5590
person.identifier.scopus-author-id55354413900
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
relation.isAuthorOfPublication953b69db-f6a0-4a54-8618-93a912df6df6
relation.isAuthorOfPublication238ee6f8-61cd-49b4-9392-9e7763fd35f3
relation.isAuthorOfPublication9cd470af-3968-45cc-ad6f-3b59e00ae823
relation.isAuthorOfPublication.latestForDiscovery953b69db-f6a0-4a54-8618-93a912df6df6
relation.isProjectOfPublication32dd2667-ca4e-430b-a130-687ba6eee2e9
relation.isProjectOfPublication.latestForDiscovery32dd2667-ca4e-430b-a130-687ba6eee2e9

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
TAFFC - Percussion_and_Instrumentation_in_Music_Emotion_Recognition__a_Feature_Engineering_Approach - preprint.pdf
Size:
2.68 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.85 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

IPT - Ci2 - Artigos em Revistas Científicas