Less acoustic features means more statistical relevance: Disclosing the clustering behavior in music stimuli

Página do item simplificado
dc.contributor.authorRIBEIRO, E.
dc.contributor.authorCarlos E. Thomaz
dc.contributor.authorOrcidhttps://orcid.org/0000-0001-5566-1963
dc.date.accessioned2022-03-01T06:04:55Z
dc.date.available2022-03-01T06:04:55Z
dc.date.issued2022-04-05
dc.description.abstractIdentification of appropriate content-based features for the description of audio signals can provide a better repre-sentation of naturalistic music stimuli which, in recent years, have been used to understand how the human brain processes such information. In this work, an extensive clustering analysis has been carried out on a large and benchmark audio dataset to assess whether features commonly extracted in the literature are in fact statistically relevant. Our results show that not all of these well-known acoustic features might be statistically necessary. We also demonstrate quantitatively that, regardless of the musical genre, the same acoustic feature is selected to represent each cluster. This finding discloses that there is a general redundancy among the set of audio descriptors used, that does not depend on a particular music track or genre, allowing an expressive reduction of the number of features necessary to identify apropriate time instants on the audio for further brain signal processing of music stimuli.
dc.description.firstpage686
dc.description.issuenumber4
dc.description.lastpage692
dc.description.volume20
dc.identifier.citationRIBEIRO, E.; THOMAZ, C. E. Less acoustic features means more statistical relevance: Disclosing the clustering behavior in music stimuli. IEEE Latin America Transactions, v. 20, n. 4, p. 686-692, apr. 2022.
dc.identifier.doi10.1109/TLA.2022.9675475
dc.identifier.issn1548-0992
dc.identifier.urihttps://repositorio.fei.edu.br/handle/FEI/4420
dc.relation.ispartofIEEE Latin America Transactions
dc.rightsAcesso Restrito
dc.subject.otherlanguageAudio analysis
dc.subject.otherlanguageCluster analysis
dc.subject.otherlanguageMusic
dc.titleLess acoustic features means more statistical relevance: Disclosing the clustering behavior in music stimuli
dc.typeArtigo
fei.scopus.citations1
fei.scopus.eid2-s2.0-85123696335
fei.scopus.subjectAcoustic features
fei.scopus.subjectAudio analysis
fei.scopus.subjectAudio signal
fei.scopus.subjectBrain process
fei.scopus.subjectClustering analysis
fei.scopus.subjectClusterings
fei.scopus.subjectContent-based features
fei.scopus.subjectDescriptors
fei.scopus.subjectHuman brain
fei.scopus.subjectMusical genre
fei.scopus.updated2024-07-01
fei.scopus.urlhttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85123696335&origin=inward
Arquivos
Coleções
Artigos