Welcome to FouCluster’s documentation!¶
Motivation¶
Recommendation song systems nowadays, like Spotify, use song clustering by made up parameters such as danceability, energy, instrumentalness, … etc, which need an expert in that area to create those parameters.
In order to avoid expert knowledge and make access to machine learning applied to song easier, this library use signal analysis for measuring distances between songs. Because musical notes have associated frequencies, this proposal is based on transforming from time series to frequency series, and then grouping theses series using various techniques and distance metrics.
Use¶
The process to do the clustering can be divided in different steps
Contents:
An example is explained in
Contents:
It is also necessary install mpg123 or ffmpeg for MP3 to WAV transform. For Ubuntu, it is as easy as
sudo apt install mpg123