Beatbox Classification Using ACE

This paper describes the use of the Autonomous Classification Engine (ACE) to classify beatboxing (vocal percussion) sounds. A set of unvoiced percussion sounds belonging to five classes (bass drum, open hihat, closed hihat and two types of snare drum) were recorded and manually segmented. ACE was used to compare various classification techniques, both with and without feature selection. The best result was 95.55% accuracy using AdaBoost with C4.5 decision tress.

• Type: Conference
• Year: 2005
• Where: ISMIR
• Authors: Elliot Sinyor, Cory McKay, Rebecca Fiebrink, Daniel McEnnis, Ichiro Fujinaga
• Keywords: Autonomous Classification Engine, Information Retrieval, ISMIR 2005, Various Classification Techniques, Vocal Percussion