CNN based musical instrument identification using time-frequency localized features

Abstract

In this paper, the authors make an attempt to solve the convoluted problem of identifying musical instruments based on their audio excerpts, using a deep convolutional neural network. Continuous wavelet transform of audio signals are realized through Morse wavelet and two-dimensional feature maps are formed, which are then fed to a simple yet robust convolutional neural network. The outcome is appreciable in the sense that training the model with just 20% of the data and testing on the rest gives a classification accuracy of 85%.