Pré-Publication, Document De Travail Année : 2025

The Inverse Drum Machine: Source Separation Through Joint Transcription and Analysis-by-Synthesis

Résumé

We present the Inverse Drum Machine (IDM), a novel approach to drum source separation that leverages an analysis-by-synthesis framework combined with deep learning. Unlike recent supervised methods that require isolated stem recordings, our approach operates on drum mixtures with only transcription annotations. IDM integrates Automatic Drum Transcription and One-shot Drum Sample Synthesis, jointly optimizing these tasks in an end-to-end manner. By convolving synthesized one-shot samples with estimated onsets—akin to a drum machine—we reconstruct the individual drum stems and train a deep neural network on the reconstruction of the mixture. Experiments on the StemGMD dataset demonstrate that IDM achieves separation quality comparable to state-of-the-art supervised methods that require isolated stems, while significantly outperforming matrix decomposition baselines.

Fichier principal
Vignette du fichier
main.pdf (15.67 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05056592 , version 1 (05-05-2025)
hal-05056592 , version 2 (24-09-2025)

Licence

Identifiants

  • HAL Id : hal-05056592 , version 1

Citer

Bernardo Torres, Geoffroy Peeters, Gael Richard. The Inverse Drum Machine: Source Separation Through Joint Transcription and Analysis-by-Synthesis. 2025. ⟨hal-05056592v1⟩
3259 Consultations
344 Téléchargements

Partager

  • More