This publication addresses the identification of drum patterns and the classification of their musical genres. Drum patterns are estimated from audio data automatically. This process involves the transcription of percussive un-pitched instruments with a method based on Independent Subspace Analysis and a robust estimation of tatum grid and musical meter. Subsequently, patterns are identified from histograms, describing the frequency of occurrence of the percussive events on distinct metric positions. Various high-level features are derived from the drum patterns by identifying typical playing styles. The classification procedure evaluates these features in combination with information on musical meter and occurring instruments.
Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member and would like to subscribe to the E-Library then Join the AES!
This paper costs $33 for non-members and is free for AES members and E-Library subscribers.