jarovaisanen / DrumOnsetDetectionCNN

Audio data preprocessing and Convolutional Neural Network training algorithm for detecting drum onsets from polyphonic music.

DrumOnsetDetectionCNN

Installation

Drum Onset Detection CNN

Audio data preprocessing and Convolutional Neural Network training algorithm for detecting drum onsets from polyphonic music.

Table of Contents

1. About The Project
2. Getting Started
   • Prerequisites
   • Installation
3. Usage
4. Further development
5. License
6. Contact
7. Acknowledgements

About The Project

This project was implemented as part of my Master's Thesis in University of Jyväskylä, in the department of Mathematical Information Technology.

https://www.jyu.fi/en/

Getting Started

To get a local copy up and running follow these steps.

Prerequisites

• Python 3.6+

Installation

1. Clone the repo

   git clone https://github.com/jarovaisanen/DrumOnsetDetectionCNN.git

2. Install pip packages

   pip install -r requirements.txt

3. Install CUDA 10.1 for GPU accelerated CNN training:
4. Get the ENST Drum database dataset
5. Recommended to setup a virtual environment

Usage

1. Modify main.py to suit your needs (Hyperparameters, Paths)
2. Start data pre-processing and training the CNN by running main.py

Further development

The field is open for further development

1. Fork the project
2. Improve the method

License

Distributed under the MIT License. See LICENSE for more information.

Contact

Jaro Väisänen - [e-mail]

Project Link: https://github.com/jarovaisanen/DrumOnsetDetectionCNN

Acknowledgements

Master's Thesis (in Finnish)

Original article

• Automatic drum transcription with convolutional neural networks Céline Jacques, Axel Roebel. Automatic drum transcription with convolutional neural networks. 21th International Conference on Digital Audio Effects, Sep 2018, Aveiro, Portugal, Sep 2018, Aveiro,Portugal. hal-02018777

Code that helped me to get started

• Bokoch