The Inverse Drum Machine: Source Separation Through Joint Transcription and Analysis-by-Synthesis
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 31 of its 62 references that are in the map. First posted on arXiv 6 May 2025.
Builds on
31 of 62 references.
References · 31
- 2016Layer Normalizationcited by 5,579
- 2022A ConvNet for the 2020scited by 3,545
- 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
- 2018SDR - half-baked or well done?cited by 420
- 2020DDSP: Differentiable Digital Signal Processingcited by 177
- 2017Onsets and Frames: Dual-Objective Piano Transcriptioncited by 93
- 2021Hybrid Spectrogram and Waveform Source Separationcited by 90
- 2019Neural source-filter waveform models for statistical parametric speech synthesiscited by 46
- 2021Music Demixing Challenge 2021cited by 38
- 2021CRASH: Raw Audio Score-based Generative Modeling for Controllable High-resolution Drum Sound Synthesiscited by 37
- 2020DrumGAN: Synthesis of Drum Sounds With Timbral Feature Conditioning Using Generative Adversarial Networkscited by 34
- 2019Learning to Groove with Inverse Sequence Transformationscited by 33
19 more
- 2023A Review of Differentiable Digital Signal Processing for Music & Speech Synthesiscited by 19
- 2019Simultaneous Separation and Transcription of Mixtures with Multiple Polyphonic and Percussive Instrumentscited by 17
- 2020Improving Perceptual Quality of Drum Transcription with the Expanded Groove MIDI Datasetcited by 16
- 2022Sinusoidal Frequency Estimation by Gradient Descentcited by 15
- 2021Objective Measures of Perceptual Audio Quality Reviewed: An Evaluation of Their Application Domain Dependencecited by 14
- 2020The Effect of Spectrogram Reconstruction on Automatic Music Transcription: An Alternative Approach to Improve Transcription Accuracycited by 10
- 2019Neural Drum Machine : An Interactive System for Real-time Synthesis of Drum Soundscited by 8
- 2019Neural Percussive Synthesis Parameterised by High-Level Timbral Featurescited by 8
- 2023Unsupervised Harmonic Parameter Estimation Using Differentiable DSP and Spectral Optimal Transportcited by 8
- 2019Deep Unsupervised Drum Transcriptioncited by 7
- 2018Towards multi-instrument drum transcriptioncited by 5
- 2023Blind estimation of audio effects using an auto-encoder approach and differentiable digital signal processingcited by 5
- 2020wav2shape: Hearing the Shape of a Drum Machinecited by 4
- 2022Unsupervised Music Source Separation Using Differentiable Parametric Source Modelscited by 4
- 2022Differentiable Digital Signal Processing Mixture Model for Synthesis Parameter Extraction from Mixture of Harmonic Soundscited by 4
- 2023Toward Deep Drum Source Separationcited by 4
- 2023Differentiable Modelling of Percussive Audio with Transient and Spectral Synthesiscited by 3
- 2024A fully differentiable model for unsupervised singing voice separationcited by 2
- 2024Sines, Transient, Noise Neural Modeling of Piano Notescited by 1
Built on by
Citing papers per year: 2026: 3.
3 papers.