Forró em Vinil Dataset

In the work described in the paper <em>Measuring disruption in song similarity networks</em>, Falcão et al. developed a study of disruption measurement over a collection of a Brazilian music tradition called Forró. This dataset contains all the audio information used during analysis. 27,352 audio files were used to build a song similarity network, from which disruption information was derived. <em>list_songs.txt</em> and <em>list_features.txt</em> contain an indexed list of all the audio files analysed and their MFCC-based feature vectors, respectivelly. Data from both files can be mapped by using the indexes (i.e., the i-eth line in <em>list_features.txt</em> refers to the feature vector for the i-eth song informed by <em>list_songs.txt</em>) <em>Similiarity Network.txt</em> contains the similarity network built according to the similarities calculated between the feature vectors. The network is presented in a GEXF (<em>Graph Exchange XML Format)</em> format, and can be visualized with softwares like Gephi. <em>Disruption Ranking.txt</em> summarizes the Disruption Indexes of all songs, in ascending order.