Genetic programming for musical sound analysis

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