Musical Instrument Classification Utilizing a Neural Network

This paper discusses a method for classifying musical instrument audio signals utilizing a neural network. This research will identify the most salient features to evaluate within a neural network that will quickly detect an instrument from another. Feature extraction and selection are crucial steps in helping distinguish musical signals. Feature extraction is the process of obtaining specific characteristics from a data sample. Feature selection is the process that follows extraction in which the most relevant features are chosen to represent each sample. Once relevant features are selected they are applied to the neural network as possible inputs. In this study, the neural network distinguishes between two classes of instruments (e.g., trumpet or tuba). Various features are evaluated to identify which elements worked best.