Home  Publications  Softwares The Latin Music Database

 

The Latin Music Database

 

About

The Latin Music Database contains 3.160 music pieces in MP3 Format classified in 10 diferent musical genres. The musical genres used are: Tango, Bolero, Batchata, Salsa, Merengue, Axé, Forró, Sertaneja, Gaúcha and Pagode. More information about the database and the genre classification process can be found in the paper " The Latin Music Database: Uma Base de Dados Para a Classificação Automática de Gêneros Musicais" (in Portuguese) presented at the 11th Brazilian Symposium on Computer Music (SBCM) in 2007.

Download the Feature Vectors Extracted from the Latin Music Database

Due to copyright issues it is not possible to have direct access to the Latin Music Database. However the following links contain the normalized feature vectors in the .arff format used in our experiments with the database. The Marsyas was used to extract the feature vectors. In our experiments we have used a segmentation strategy which uses feature vectors extract from different parts of the music signal.

  • Feature Vectors extracted from the initial (30 seconds) of the music pieces: LMD-Begin.zip
  • Feature Vectors extracted from the middle (30 seconds) of the music pieces: LMD-Middle.zip
  • Feature Vectors extracted from the end (30 seconds) of the music pieces:: LMD-End.zip

Note: In our previous experiments we used 10-fold cross-validation and for that reason the files are identificated regarding which fold was used. Also more information concerning the use of three feature vectores instead of only one can be found soon in the paper "Automatic Music Genre Classification Using Ensemble of Classifiers" which is going to appear at the  IEEE International Conference on Systems, Man and Cybernetics (SMC2007) or in my Master's Thesis "Combinação de Classificadores para a Classificação Automática de Gêneros Musicais" (in Portuguese).

Contact

Further information about the Latin Music Database as well as informationg concerning joint research can be obtained at the following e-mail address: silla at ppgia.pucpr.br.

 

 

This Web Page Created with PageBreeze Free Website Builder