Individual Violin Recognition Method Combining Tonal and Nontonal Features

Abstract

Individual recognition among instruments of the same type is a challenging problem and it has been rarely investigated. In this study, the individual recognition of violins is explored. Based on the source–filter model, the spectrum can be divided into tonal content and nontonal content, which reflects the timbre from complementary aspects. The tonal/nontonal gammatone frequency cepstral coefficients (GFCC) are combined to describe the corresponding spectrum contents in this study. In the recognition system, Gaussian mixture models–universal background model (GMM–UBM) is employed to parameterize the distribution of the combined features. In order to evaluate the recognition task of violin individuals, a solo dataset including 86 violins is developed in this study. Compared with other features, the combined features show a better performance in both individual violin recognition and violin grade classification. Experimental results also show the GMM–UBM outperforms the CNN, especially when the training data are limited. Finally, the effect of players on the individual violin recognition is investigated.

Violinist Identification Using Note-Level Timbre Feature Distributions

“…We use three classifiers including K-Nearest Neighbour (KNN), Gaussian Mixture Model with KL divergence (GMM-KL) and Gaussian Mixture Model with Universal Background Model (GMM-UBM) as baseline, and MFCCs are set as input feature because these perform best in previous works as well as in our proposed method. These baseline methods are used for violinist identification [10], music similarity estimation [22], and violin classification [23], therefore we adopt them as baseline to identify violinists for both datasets, the details of data split and experiment setup are kept the same as in the experiments in Section 4.2 and Section 4.3.…”