Metadata for Audio 25th International AES Conference 17th to 19th June 2004 London UK
Home
Programme
Venue
Registration
Important dates
Contact information
OverviewProgrammePapers by session


Metadata for Audio



Poster CD2-5

Efficient Musical Instrument Recognition On Solo Performance Music Using Basic Features

Slim Essid, Ga�l Richard, Bertrand David
GET-T�l�com Paris (ENST), Paris, France

Musical instrument recognition has gained growing concern for the promise it holds towards advances in musical content description. The present study pursues the goal of showing the efficiency of some basic features for such a recognition task in the realistic situation where solo musical phrases are played. A large and varied database of sounds assembled from different commercial recordings is used to ensure better training and testing conditions, in terms of statistical efficiency. It is found that when combining cepstral features with others describing the audio signal spectral shape, a high recognition accuracy can be achieved in association with Support Vector Machine classification (especially when using a Radial Basis Function kernel).

Conference logo