Introduction
May 26, 2016 ยท View on GitHub
// DrumPtDataset V1.00 // Latest update: May 2016
Introduction
DrumPtDataset is a collection of datasets that are created for drum playing technique detection related research. The dataset contains three folders:
-
Parameter_estimation: this folder contains annotations and MATLAB scripts for estimating the parameters of Flam and Drag from the online drum lesson videos.
-
Testing_set: this folder contains annotations of drum playing techniques for the ENST drum minus one subset.
-
Training_set_gen: this folder contains the MATLAB scripts for augmenting the existing MDLib2.2 with synthetic Flam and Drag audio samples. The audio files are not provided due to the copyright restrictions.
For more detailed information, please refer to the following publication:
Chih-Wei Wu, Alexander Lerch, On Drum Playing Technique Detection in Polyphonic Mixtures, in Proceedings of the International Conference on Music Information Retrieval (ISMIR), New York, 2016.
Usage
Please refer to the README.txt in each individual folder for further instructions.
Contact
Chih-Wei Wu cwu307@gatech.edu
Georgia Tech Center for Music Technology 840 McMillan Street Atlanta, GA 30332