Applying supervised learning techniques to Brazilian music genre classification

In this work, an initial study on the automatic recognition of the main Brazilian music genres is presented: Axe, Forro, MPB, Rock, Samba, and Sertanejo. Through the extraction of representative musical characteristics, automatic classification experiments were performed applying classical supervised learning algorithms and Weka ML tool. An analysis of the main available databases was also carried out: GTZAN, FMA, AudioSet, RWC, ISMIR, Magnatune, and LMD. There is a scarcity of cultural diversity on these bases, most of which concentrate globally more popular styles such as Pop and Rock, reinforcing the need to include more diverse and culturally identifiable genres, such as Brazilians. The preliminary results obtained demonstrate the adequacy of the recognition process of the main Brazilian musical genres.