The Inverse Drum Machine: Source Separation Through Joint Transcription and Analysis-by-Synthesis
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916978075107328 |
|---|---|
| author | Torres, Bernardo Peeters, Geoffroy Richard, Gael |
| author_facet | Torres, Bernardo Peeters, Geoffroy Richard, Gael |
| contents | We present the Inverse Drum Machine, 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 for training, our approach is trained 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 data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_03337 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | The Inverse Drum Machine: Source Separation Through Joint Transcription and Analysis-by-Synthesis Torres, Bernardo Peeters, Geoffroy Richard, Gael Sound Audio and Speech Processing Signal Processing Machine Learning We present the Inverse Drum Machine, 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 for training, our approach is trained 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 data. |
| title | The Inverse Drum Machine: Source Separation Through Joint Transcription and Analysis-by-Synthesis |
| topic | Sound Audio and Speech Processing Signal Processing Machine Learning |
| url | https://arxiv.org/abs/2505.03337 |