mlsanityData to 7 Oct 2026

Toward Deep Drum Source Separation

arXiv 2312.09663 ↗First posted 15 Dec 2023eess.AS cs.LG cs.SDcited by 4

Not on the map. Why?

Abstract (arXiv)

In the past, the field of drum source separation faced significant challenges due to limited data availability, hindering the adoption of cutting-edge deep learning methods that have found success in other related audio applications. In this manuscript, we introduce StemGMD, a large-scale audio dataset of isolated single-instrument drum stems. Each audio clip is synthesized from MIDI recordings of expressive drums performances using ten real-sounding acoustic drum kits. Totaling 1224 hours, StemGMD is the largest audio dataset of drums to date and the first to comprise isolated audio clips for every instrument in a canonical nine-piece drum kit. We leverage StemGMD to develop LarsNet, a novel deep drum source separation model. Through a bank of dedicated U-Nets, LarsNet can separate five stems from a stereo drum mixture faster than real-time and is shown to significantly outperform state-of-the-art nonnegative spectro-temporal factorization methods.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 15 of its 35 references that are in the map. First posted on arXiv 15 Dec 2023.

Builds on

15 of 35 references.

References · 15

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  3. 2017Supervised Speech Separation Based on Deep Learning: An Overviewcited by 213
  4. 2021Hybrid Spectrogram and Waveform Source Separationcited by 90
  5. 2018The 2018 Signal Separation Evaluation Campaigncited by 41
  6. 2019Universal Sound Separationcited by 41
  7. 2021Music Demixing Challenge 2021cited by 38
  8. 2019Learning to Groove with Inverse Sequence Transformationscited by 33
  9. 2020All for One and One for All: Improving Music Separation by Bridging Networkscited by 20
  10. 2023The Sound Demixing Challenge 2023 unicodex2013 Music Demixing Trackcited by 20
  11. 2020Meta-learning Extractors for Music Source Separationcited by 18
  12. 2020Improving Perceptual Quality of Drum Transcription with the Expanded Groove MIDI Datasetcited by 16
3 more
  1. 2019Deep Unsupervised Drum Transcriptioncited by 7
  2. 2018Towards multi-instrument drum transcriptioncited by 5
  3. 2021Global Structure-Aware Drum Transcription Based on Self-Attention Mechanismscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2025The Inverse Drum Machine: Source Separation Through Joint Transcription and Analysis-by-Synthesiscited by 3
  2. 2026Towards Realistic Synthetic Data for Automatic Drum Transcriptioncited by 1
  3. 2026Break-the-Beat! Controllable MIDI-to-Drum Audio Synthesiscited by 0
  4. 2026Separate-and-Detect: Unified Drum Transcription and Stem Generation via Latent Diffusioncited by 0