This study uses Genetic Programming (GP) in developing
a classi er to distinguish between ve musical instruments. Using only
simple arithmetic and boolean operators with 95 features as terminals,
a program is developed that can classify 300 unseen samples with an
accuracy of 94%. The experiment is then run again using only 14 of
the most often chosen features. Limiting the features in this way raised
the best classi cation to 94.3% and the average accuracy from 68.2% to
75.67%. This demonstrates that not only can GP be used to create a
classi er but it can be used to determine the best features to choose for
accurate musical instrument classi cation, giving an insight into timbre
History
Publication
Evolutionary and Biologically Inspired Music, Sound, Art and Design: EvoMUSART 2012 Machado P., Romero J., Carballal A. (eds): Lecture Notes in Computer Science, vol 7247
Publisher
Springer
Note
peer-reviewed
Other Funding information
SFI
Rights
The original publication is available at www.springerlink.com