Author(s): Rocha, Bruno ; Panda, Renato ; Paiva, Rui Pedro
Date: 2013
Persistent ID: https://hdl.handle.net/10316/95166
Origin: Estudo Geral - Universidade de Coimbra
Project/scholarship: info:eu-repo/grantAgreement/FCT/5876-PPCDTI/102185/PT ;
Subject(s): audio; machine learning; melodic features; music emotion recognition
We study the importance of a melodic audio (MA) feature set in music emotion recognition (MER) and compare its performance to an approach using only standard audio (SA) features. We also analyse the fusion of both types of features. Employing only SA features, the best attained performance was 46.3%, while using only MA features the best outcome was 59.1% (F- measure). A combination of SA and MA features improved results to 64%. These results might have an important impact to help break the so-called glass ceiling in MER, as most current approaches are based on SA features.
This work was supported by the MOODetector project (PTDC/EIA-EIA/102185/2008), financed by the Fundação para Ciência e a Tecnologia (FCT) and Programa Operacional Temático Factores de Competitividade (COMPETE) - Portugal.
