We introduce the Inverse Drum Machine (IDM), a novel approach to drum source separation that combines analysis-by-synthesis with deep learning. Unlike recent supervised methods that rely on isolated stems, IDM requires only transcription annotations. It jointly optimizes automatic drum transcription and one-shot drum sample synthesis in an end-to-end framework. By convolving synthesized one-shot samples with estimated onsets-mimicking a drum machine-IDM reconstructs individual drum stems and trains a neural network to match the original mixture. Evaluations on the StemGMD dataset show that IDM achieves separation performance on par with state-of-the-art supervised methods, while substantially outperforming matrix decomposition baselines.
View on arXiv@article{torres2025_2505.03337,
title={ The Inverse Drum Machine: Source Separation Through Joint Transcription and Analysis-by-Synthesis },
author={ Bernardo Torres and Geoffroy Peeters and Gael Richard },
journal={arXiv preprint arXiv:2505.03337},
year={ 2025 }
}