Three Datasets created from a bank of Brazilian Popular Songs of Success and Non-Success from 2014 to 2019
Abstract
This work deals with the creation and optimization of a large set of characteristics extracted from a bank of 881 popular Brazilian Hit-Songs and Non Hit-Songs, between January 2014 and May 2019. From this bank of songs, three DataSets were created of distinct features, the first of which contains 3215 statistical features; the second and third are completely new, as they were formed from the Vocal Melody of the songs (Predominant Voice Melody), with no similar database available for research. The second bank represents a spectrogram graph, formed from the initial 90 seconds of each song. The third bank is the most peculiar of all, as it represents a musical semantic analysis of the second bank, where the main purpose was to build a table composed of the most frequent melodic sequences of each song. Our Datasets use only Brazilian songs and focus your data on a limited and contemporary period. The idea behind creating these datasets is to encourage the study of Machine Learning techniques that require musical information. The resources extracted may help in the development of new research in the areas of music and computing in the future.
References
Bertin-Mahieux, T., Ellis, D. P., Whitman, B., and Lamere, P. (2011). The million song dataset.
Blume, J. (2019). What makes a song a hit?
Bogdanov, D., Wack, N., Gómez, E., Gulati, S., Herrera, P., Mayor, O., Roma, G., Salamon, J., Zapata, J. R., and Serra, X. (2013). Essentia: an audio analysis library for music information retrieval. In International Society for Music Information Retrieval Conference (ISMIR’13), pages 493–498, Curitiba, Brazil.
ConnectMIX (2019). Connectmix, monitoramento, auditoria e gestão de áudio em tempo real em rádios e tvs.
IBGE (2021). População do brasil.
Olteanu, A. (2020). Gtzan dataset - music genre classification.
Raieli, R. (2013). Multimedia Information Retrieval: theory and techniques. Elsevier.
Salamon, J. (2013). Melody Extraction from Polyphonic Music Signals. PhD thesis, Universitat Pompeu Fabra, Barcelona, Spain.
