With this toolbox, we provide an easy way of accessing and interacting with the ChoraleBricks dataset.

For an overview of the dataset, please visit our demo website:
https://audiolabs-erlangen.de/resources/MIR/2025-ChoraleBricks

If you use ChoraleBricks in your academic work, please cite this article:

📘 Stefan Balke, Axel Berndt, and Meinard Müller ChoraleBricks: A Modular Multitrack Dataset for Wind Music Research Transactions of the International Society for Music Information Retrieval, 2025.

@article{BalkeBM24_ChoraleBricks,
  author  = {Stefan Balke and Axel Berndt and Meinard M{\"u}ller},
  title   = {{ChoraleBricks}: A Modular Multitrack Dataset for Wind Music Research},
  journal = {Transactions of the International Society for Music Information Retrieval},
  volume = {8},
  number = {1},
  pages = {39--54},
  year = {2025},
  doi = {10.5334/tismir.252}
}

💻 Installation and Setup

Warning

This repository currently supports parsing ChoraleBricks v1.1 and ChoraleWind v1.0, it is not backwards compatible. If you want to use this repo with ChoraleBricks v1.0.x, please use an older version tag in GitHub.

Clone repository, then:

pip install uv
uv sync

Download the corresponding audio files from Zenodo:

https://zenodo.org/records/15463260

Usage

To use the full dataset, set a dataset root_dir directory

cbdb = SongDB(root_dir="/path/to/ChoraleBricks")

where root_dir is the path to the ChoraleDB dataset folder. The root_dir can also be overridden using a system environment variable. For example:

# bash / zsh
export CHORALEDB_PATH=/path/to/ChoraleBricks

In that case no arguments would need to passed to SongDB().

Further example scripts for different standard scenarios can be found in the examples/ folder.

Examples

As a starting point, we provide example code in the examples/ folder. These require slightly more dependencies. Use:

uv sync --extra examples

for setup.

Glossary

song

In this dataset, it groups all tracks of a certain chorale together.

track

A single track in a multi-track recording.

voice

Each chorale consists of 4 voices sometimes referred to sopran, alt, tenor, and bass (SATB).

ensemble

An ensemble is in the context of ChoraleBricks a set of four tracks (S, A, T, B).

How to contribute

ChoraleDB is a community focused project, we therefore encourage the community to submit bug-fixes and requests for technical support through GitHub issues.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgements

This work was funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under grant number 500643750 (MU 2686/15-1) and under Grant No. 555525568 (MU 2686/18-1). The International Audio Laboratories Erlangen are a joint institution of the Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) and Fraunhofer Institute for Integrated Circuits IIS.