Drum Stroke Computing: Multimodal Signal Processing for Drum Stroke Identification and Performance Metrics

In this paper we present a multimodal system for analyzing drum performance. In the first example we perform automatic drum hand recognition utilizing a technique for automatic labeling of training data using direct sensors, and only indirect sensors (e.g. a microphone) for testing. Left/Right drum hand recognition is achieved with an average accuracy of 84.95% for two performers. Secondly we provide a study investigating multimodality dependent performance metrics analysis.