Study on the classification of beatbox sounds based on timbre features

Beatbox is a performance form of vocal percussion, which is gradually favored by people with continuous development in recent years. With the abundance of Beatbox content on the Internet, the research on its automatic classification becomes very significant. In this article, we mainly using machine learning methods, to identify the beatbox timbre. First of all, we collected 900 Beatbox audio materials and constructed a database. Secondly, 14 acoustic parameters of audio material are extracted by the signal processing method. Finally, we used MultilayerPerceptron, SMO, BayesNet, RandomForest in current machine learning to build a training model for BB timbre classification. The Experimental results showed that the model could classify BB timbre well.