On the Relevance of Spectral Features for Instrument Classification

Abstract

Automatic knowledge extraction from music signals is a key component for most music organization and music information retrieval systems. In this paper, we consider the problem of instrument modelling and instrument classification from the rough audio data. Existing systems for automatic instrument classification operate normally on a relatively large number of features, from which those related to the spectrum of the audio signal are particularly relevant. In this paper, we confront two different models about the spectral characterization of musical instruments. The first assumes a constant envelope of the spectrum (i.e., independent from the pitch), whereas the second assumes a constant relation among the amplitude of the harmonics. The first model is related to the Mel Frequency Cepstrum Coefficients (MFCCs), while the second leads to what we will refer to as Harmonic Representation (HR). Experiments on a large database of real instrument recordings show that the first model offers a more satisfactory characterization, and therefore MFCCs should be preferred to HR for instrument modelling/classification.

Multiscale Fractal Analysis of Musical Instrument Signals With Application to Recognition

“…The results favored the MFCC features, which were more accurate in instrument family classification. Experiments on real instrument recordings [21] also favored the MFCCs over harmonic representations.…”

An exploration of genetic algorithms for efficient musical instrument identification

“…Each study created a classifier to distinguish between a given set of instruments from a selection of timbral features. Such studies have used Multi-layered Perceptrons [2,3], k-Nearest Neighbour [4,5] and Support Vector Machines [6,7] among others, as classifiers. An exhaustive account of various classification methods used to distinguish between musical instruments is given in [8].…”

Extended Nonnegative Tensor Factorisation Models for Musical Sound Source Separation

“…This single instrument basis function is then assumed to represent the typical frequency characteristics of that instrument. This is a simplification of the real situation, where in practice, the timbre of a given instrument does change with pitch [31]. Despite this, the assumption does represent a valid approximation over a limited pitch range, and this assumption has been used in many commercial music samplers and synthesisers, where a prerecorded note of a given pitch is used to generate other notes close in pitch to the original note.…”