Music Information Retrieval systems are often based on the analysis of a large number of low-level audio features. When dealing with problems of musical genre description and visualization, however, it would be desirable to work with a very limited number of highly informative and discriminant macro-descriptors. In this paper we focus on a specific class of training-based descriptors, which are obtained as the loglikelihood of a Gaussian Mixture Model trained with short musical excerpts that selectively exhibit a certain semantic homogeneity. As these descriptors are critically dependent on the training sets, we approach the problem of how to automatically generate suitable training sets and optimize the associated macro-features in terms of discriminant power and informative impact. We then show the application of a set of three identified macro-features to genre visualization, tracking and classification.

Searching for dominant high-level features for music information retrieval

ZANONI, MASSIMILIANO;CIMINIERI, DANIELE;SARTI, AUGUSTO;TUBARO, STEFANO
2012

Abstract

Music Information Retrieval systems are often based on the analysis of a large number of low-level audio features. When dealing with problems of musical genre description and visualization, however, it would be desirable to work with a very limited number of highly informative and discriminant macro-descriptors. In this paper we focus on a specific class of training-based descriptors, which are obtained as the loglikelihood of a Gaussian Mixture Model trained with short musical excerpts that selectively exhibit a certain semantic homogeneity. As these descriptors are critically dependent on the training sets, we approach the problem of how to automatically generate suitable training sets and optimize the associated macro-features in terms of discriminant power and informative impact. We then show the application of a set of three identified macro-features to genre visualization, tracking and classification.
Proceedings of the EURASIP European Signal Processing Conference
9781467310680
feature extraction; musical signal processing
File in questo prodotto:
File Dimensione Formato  
2012_EUSIPCO_dominant_high-level_features_MIR.pdf

Accesso riservato

: Post-Print (DRAFT o Author’s Accepted Manuscript-AAM)
Dimensione 562.53 kB
Formato Adobe PDF
562.53 kB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11311/693077
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 10
  • ???jsp.display-item.citation.isi??? 3
social impact