Passer à la navigation principale Passer à la recherche Passer au contenu principal

Gmm supervector for content based music similarity

  • STMS IRCAM-CNRS-UPMC

Résultats de recherche: Le chapitre dans un livre, un rapport, une anthologie ou une collection › Contribution à une conférence › Revue par des pairs

21 Citations (Scopus)

Résumé

Timbral modeling is fundamental in content based music similarity systems. It is usually achieved by modeling the short term features by a Gaussian Model (GM) or Gaussian Mixture Models (GMM). In this article we propose to achieve this goal by using the GMM-supervector approach. This method allows to represent complex statistical models by an Euclidean vector. Experiments performed for the music similarity task showed that this model outperform state of the art approches. Moreover, it reduces the similarity search time by a factor of ≈ 100 compared to state of the art GM modeling. Furthermore, we propose a new supervector normalization which makes the GMM-supervector approach more preformant for the music similarity task. The proposed normalization can be applied to other Euclidean models.

langue originaleAnglais
titreProceedings of the 14th International Conference on Digital Audio Effects, DAFx 2011
Pages425-428
Nombre de pages4
étatPublié - 1 janv. 2011
Modification externeOui
Evénement14th International Conference on Digital Audio Effects, DAFx 2011 - Paris, France
Durée: 19 sept. 2011 → 23 sept. 2011

Série de publications

NomProceedings of the International Conference on Digital Audio Effects, DAFx
ISSN (imprimé)2413-6700
ISSN (Electronique)2413-6689

Une conférence

Une conférence14th International Conference on Digital Audio Effects, DAFx 2011
Pays/TerritoireFrance
La villeParis
période19/09/11 → 23/09/11

Empreinte digitale

Examiner les sujets de recherche de « Gmm supervector for content based music similarity ». Ensemble, ils forment une empreinte digitale unique.

Contient cette citation