PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Audio Music Classification Using A Combination Of Spectral, Timbral, Rhythmic, Temporal And Symbolic Features
Thomas Lidy, Andreas Rauber, Antonio Pertusa, Pedro J. Ponce de León and José Iñesta
In: MIREX 2008, 17 Dec 2008, Philadelphia, USA.


The novel approach of combining audio and symbolic features for music classification from audio enhanced previous audio-only based results in MIREX 2007. We extended the approach by including temporal audio features, enhancing the polyphonic audio to MIDI transcription system and including an extended set of symbolic features. Recent research in music genre classification hints at a glass ceiling being reached using timbral audio features.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Poster)
Project Keyword:Project Keyword UNSPECIFIED
ID Code:5792
Deposited By:José Iñesta
Deposited On:08 March 2010