mlsanityData to 7 Oct 2026

Benchmarks and leaderboards for sound demixing tasks

arXiv 2305.07489 ↗First posted 12 May 2023cs.SD cs.LG eess.AScited by 6

Not on the map. Why?

Abstract (arXiv)

Music demixing is the task of separating different tracks from the given single audio signal into components, such as drums, bass, and vocals from the rest of the accompaniment. Separation of sources is useful for a range of areas, including entertainment and hearing aids. In this paper, we introduce two new benchmarks for the sound source separation tasks and compare popular models for sound demixing, as well as their ensembles, on these benchmarks. For the models' assessments, we provide the leaderboard at https://mvsep.com/quality_checker/, giving a comparison for a range of models. The new benchmark datasets are available for download. We also develop a novel approach for audio separation, based on the ensembling of different models that are suited best for the particular stem. The proposed solution was evaluated in the context of the Music Demixing Challenge 2023 and achieved top results in different tracks of the challenge. The code and the approach are open-sourced on GitHub.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 14 of its 29 references that are in the map. First posted on arXiv 12 May 2023.

Builds on

14 of 29 references.

References · 14

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2022Hybrid Transformers for Music Source Separationcited by 134
  4. 2018Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separationcited by 125
  5. 2019Music Source Separation in the Waveform Domaincited by 98
  6. 2021Hybrid Spectrogram and Waveform Source Separationcited by 90
  7. 2022Music Source Separation with Band-split RNNcited by 69
  8. 2021Decoupling Magnitude and Phase Estimation with Deep ResUNet for Music Source Separationcited by 48
  9. 2018The 2018 Signal Separation Evaluation Campaigncited by 41
  10. 2021Music Demixing Challenge 2021cited by 38
  11. 2021Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Datacited by 27
  12. 2021KUIELab-MDX-Net: A Two-Stream Neural Network for Music Demixingcited by 24
2 more
  1. 2021The Cocktail Fork Problem: Three-Stem Audio Separation for Real-World Soundtrackscited by 19
  2. 2019Singing voice separation: a study on training datacited by 5

Built on by

Cited by year (2026 to 7 Oct)

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

6 papers.

  1. 2025Emilia: A Large-Scale, Extensive, Multilingual, and Diverse Dataset for Speech Generationcited by 19
  2. 2025MIKU-PAL: An Automated and Standardized Multi-Modal Method for Speech Paralinguistic and Affect Labelingcited by 3
  3. 2025Event2Audio: Event-Based Optical Vibration Sensingcited by 3
  4. 2026Summary of The Inaugural Music Source Restoration Challengecited by 1
  5. 2026Dialogue-Aware Video-to-Music Generation Using Public Domain Film Collectionscited by 1
  6. 2026A Knowledge-Driven Approach to Music Segmentation, Music Source Separation and Cinematic Audio Source Separationcited by 0