Automatic selection of acoustic features using a lazy spitting method

The increasing amount of music data approaching the scale of ten million of tracks poses the challenge of organizing such huge information. Audio Tag Classification is a sub-area in Music Information Retrieval. Its objective is to predict human motivated tags given the acoustic data. One major probl...

Descripción completa

Detalles Bibliográficos
Autores principales: Bourguigne, Simon, Agüero, Pablo Daniel, Tulli, Juan Carlos, Gonzalez, Esteban Lucio, Uriz, Alejandro Jose
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2011
Materias:
Ciencias Informáticas
music information retrieval
audio tag classification
greedy algorithm
spitting algorithm
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/125328
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-125328
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
music information retrieval
audio tag classification
greedy algorithm
spitting algorithm
spellingShingle Ciencias Informáticas
music information retrieval
audio tag classification
greedy algorithm
spitting algorithm
Bourguigne, Simon
Agüero, Pablo Daniel
Tulli, Juan Carlos
Gonzalez, Esteban Lucio
Uriz, Alejandro Jose
Automatic selection of acoustic features using a lazy spitting method
topic_facet Ciencias Informáticas
music information retrieval
audio tag classification
greedy algorithm
spitting algorithm
description The increasing amount of music data approaching the scale of ten million of tracks poses the challenge of organizing such huge information. Audio Tag Classification is a sub-area in Music Information Retrieval. Its objective is to predict human motivated tags given the acoustic data. One major problem in this procedure is the training of the classifier. An important step in the training is the selection of the appropriate acoustical features. This paper explores two selection approaches: greedy and spitting. Experimental results indicate that the proposed spitting algorithm has a superior performance both in classification (F-measure score) and speed (lower computational requirements).
format Objeto de conferencia
Objeto de conferencia
author Bourguigne, Simon
Agüero, Pablo Daniel
Tulli, Juan Carlos
Gonzalez, Esteban Lucio
Uriz, Alejandro Jose
author_facet Bourguigne, Simon
Agüero, Pablo Daniel
Tulli, Juan Carlos
Gonzalez, Esteban Lucio
Uriz, Alejandro Jose
author_sort Bourguigne, Simon
title Automatic selection of acoustic features using a lazy spitting method
title_short Automatic selection of acoustic features using a lazy spitting method
title_full Automatic selection of acoustic features using a lazy spitting method
title_fullStr Automatic selection of acoustic features using a lazy spitting method
title_full_unstemmed Automatic selection of acoustic features using a lazy spitting method
title_sort automatic selection of acoustic features using a lazy spitting method
publishDate 2011
url http://sedici.unlp.edu.ar/handle/10915/125328
work_keys_str_mv AT bourguignesimon automaticselectionofacousticfeaturesusingalazyspittingmethod
AT agueropablodaniel automaticselectionofacousticfeaturesusingalazyspittingmethod
AT tullijuancarlos automaticselectionofacousticfeaturesusingalazyspittingmethod
AT gonzalezestebanlucio automaticselectionofacousticfeaturesusingalazyspittingmethod
AT urizalejandrojose automaticselectionofacousticfeaturesusingalazyspittingmethod
bdutipo_str Repositorios
_version_ 1764820451521986563

Ejemplares similares