期刊名称：International Journal of Electronics, Communication and Soft Computing Science and Engineering
印刷版ISSN：2277-9477
出版年度：2013
卷号：2
期号：Special
出版社：IJECSCSE
摘要：Music signal is different from speech signal,therefore for recognizing musical instrument there is a need ofdesigning a different system. Here we have designed aninstrument identification system.In this paper we havediscussed the role of various features for classifying musicalinstruments with k-NN and SVM classifieridentify musical instrumentsusingFivemusical instruments: Flute, Piano, Trumpet, Guitar andXylophone are considered. From each signal of the database wehave extracted different features and thesefor training the classifiers. The trained classifierstested to identify musical instruments using unseen signalsobserved that the identification accuracy depends on thefeatures used as well as the classifier. This analthe desired classifier with all features and a desirewith a classifier to design the musical instrument identifiersystem.
