Geographical Origin of Music
Donated on 10/17/2014
Instances in this dataset contain audio features extracted from 1059 wave files. The task associated with the data is to predict the geographical origin of music.
Dataset Characteristics
Multivariate
Subject Area
Other
Associated Tasks
Classification, Regression
Feature Type
Real
# Instances
1059
# Features
68
Dataset Information
Additional Information
The dataset was built from a personal collection of 1059 tracks covering 33 countries/area. The music used is traditional, ethnic or `world' only, as classified by the publishers of the product on which it appears. Any Western music is not included because its influence is global - what we seek are the aspects of music that most influence location. Thus, being able to specify a location with strong influence on the music is central. The geographical location of origin was manually collected the information from the CD sleeve notes, and when this information was inadequate we searched other information sources. The location data is limited in precision to the country of origin. The country of origin was determined by the artist's or artists' main country/area of residence. Any track that had ambiguous origin is not included. We have taken the position of each country's capital city (or the province of the area) by latitude and longitude as the absolute point of origin. The program MARSYAS[1] was used to extract audio features from the wave files. We used the default MARSYAS settings in single vector format (68 features) to estimate the performance with basic timbal information covering the entire length of each track. No feature weighting or pre-filtering was applied. All features were transformed to have a mean of 0, and a standard deviation of 1. We also investigated the utility of adding chromatic attributes. These describe the notes of the scale being used. This is especially important as a distinguishing feature in geographical ethnomusicology. The chromatic features provided by MARSYAS are 12 per octave - Western tuning, but it may be possible to tell something from how similar to or different from Western tuning the music is. [1] G. Tzanetakis and P. Cook, “MARSYAS: a framework for audio analysis,†Organised Sound, vol. 4, pp. 169–175, 2000.
Has Missing Values?
No
Introductory Paper
By Fang Zhou, Q. Claire, Ross D. King. 2014
Published in 2014 IEEE International Conference on Data Mining
Variable Information
The dataset is present in two files, where each file corresponds to a different feature sets. Both files contain the audio features of 1059 tracks. In the 'default_features_1059_tracks.txt' file, the first 68 columns are audio features of the track, and the last two columns are the origin of the music, represented by latitude and longitude. In the 'default_plus_chromatic_features_1059_tracks.txt' file, the first 116 columns are audio features of the track, and the last two columns are the origin of the music.
Reviews
There are no reviews for this dataset yet.
pip install ucimlrepo
from ucimlrepo import fetch_ucirepo # fetch dataset geographical_origin_of_music = fetch_ucirepo(id=315) # data (as pandas dataframes) X = geographical_origin_of_music.data.features y = geographical_origin_of_music.data.targets # metadata print(geographical_origin_of_music.metadata) # variable information print(geographical_origin_of_music.variables)
Zhou,Fang. (2014). Geographical Origin of Music. UCI Machine Learning Repository. https://doi.org/10.24432/C5VK5D.
@misc{misc_geographical_origin_of_music_315,
author = {Zhou,Fang},
title = {{Geographical Origin of Music}},
year = {2014},
howpublished = {UCI Machine Learning Repository},
note = {{DOI}: https://doi.org/10.24432/C5VK5D}
}Creators
Fang Zhou
DOI
License
This dataset is licensed under a Creative Commons Attribution 4.0 International (CC BY 4.0) license.
This allows for the sharing and adaptation of the datasets for any purpose, provided that the appropriate credit is given.