Deep Conditional Representation Learning for Drum Sample Retrieval by Vocalisation

This is the code repository for the Interspeech 2022 paper (under review) Deep Conditional Representation Learning for Drum Sample Retrieval by Vocalisation by Alejandro Delgado, Charalampos Saitis, Emmanouil Benetos, and Mark Sandler.

Contents

• src – the main codebase with scripts for processing data, models, and results.
• data – datasets and processed data used throughout the study.
• models – folder that hosts already trained models.
• results – folder that hosts information relative to final accuracy results.

Requirements

To install requirements:

pip install -r requirements.txt

If you are a Mac user, you may need to install Essentia using Homebrew.

TODO List

• Finish tidying up code
• Finish commenting code
• Finish README file

Acknowledgments

This work has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No. 765068.