Genre classification using bass-related high-level features and playing styles

Considering its mediation role between the poles of rhythm, harmony, and melody, the bass plays a crucial role in most music genres. This paper introduces a novel set of transcription-based high-level features that characterize the bass and its interaction with other participating instruments. Furthermore, a new method to model and automatically retrieve different genre-specific bass playing styles is presented. A genre classification task is used as benchmark to compare common machine learning algorithms based on the presented high-level features with a classification algorithm solely based on detected bass playing styles.