Predicting the Geographical Origin of Music

By Fang Zhou, Q. Claire, Ross D. King. 2014

56 citations recorded by the source corpus.

Traditional research into the arts has almost always been based around the subjective judgment of human critics. The use of data mining tools to understand art has great promise as it is objective and operational. We investigate the distribution of music from around the world: geographical ethnomusicology. We cast the problem as training a machine learning program to predict the geographical origin of pieces of music. This is a technically interesting problem as it has features of both classification and regression, and because of the spherical geometry of the surface of the Earth. Because of these characteristics of the representation of geographical positions, most standard classification/regression methods cannot be directly used. Two applicable methods are K-Nearest Neighbors and Random forest regression, which are robust to the non-standard structure of data. We also investigated improving performance through use of bagging. We collected 1,142 pieces of music from 73 countries/areas, and described them using 2 different sets of standard audio descriptors using MARSYAS. 10-fold cross validation was used in all experiments. The experimental results indicate that Random forest regression produces significantly better results than KNN, and the use of bagging improves the performance of KNN. The best performing algorithm achieved a mean great circle distance error of 3,113 km.

Subfields: Computer Vision and Pattern Recognition, Developmental Biology, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

Supervised Dimensionality Reduction via Distance Correlation Maximization (2016, background): “(d) Geographical Origin of Music [Zhou et al., 2014]: Instances in this dataset contain audio features extracted from 1059 wave ﬁles covering 33 countries/areas.”
A topological insight into restricted Boltzmann machines (2016, methodology): “The resulting predictions were 3258 ± 175 kilometers (GRBM) and 3252 ± 176 kilometers (GXBM) which are comparable to the top performers found in Zhou et al (2014), even if it is well known that GRBMs and RBMs are not best performers on classiﬁcation and regression tasks, when used as standalone…”