Recognising Cello Performers Using Timbre Models

Abstract

In this paper, we compare timbre features of various cello performers playing the same instrument in solo cello recordings. Using an automatic feature extraction framework, we investigate the differences in sound quality of the players. The motivation for this study comes from the fact that the performer’s influence on acoustical characteristics is rarely considered when analysing audio recordings of various instruments. We explore the phenomenon, known amongst musicians as the “sound” of a player, which enables listeners to differentiate one player from another when they perform the same piece of music on the same instrument. We analyse sets of spectral features extracted from cello recordings of five players and model timbre characteristics of each performer. The proposed features include harmonic and noise (residual) spectra, Mel-frequency spectra and Mel-frequency cepstral coefficients. Classifiers such as k-Nearest Neighbours and Linear Discrimination Analysis trained on these models are able to distinguish the five performers with high accuracy.