mlsanityData to 14 Oct 2026

Moisesdb: A dataset for source separation beyond 4-stems

arXiv 2307.15913 ↗First posted 29 Jul 2023cs.SD cs.AI eess.AScited by 39

Not on the map. Why?

Abstract (arXiv)

In this paper, we introduce the MoisesDB dataset for musical source separation. It consists of 240 tracks from 45 artists, covering twelve musical genres. For each song, we provide its individual audio sources, organized in a two-level hierarchical taxonomy of stems. This will facilitate building and evaluating fine-grained source separation systems that go beyond the limitation of using four stems (drums, bass, other, and vocals) due to lack of data. To facilitate the adoption of this dataset, we publish an easy-to-use Python library to download, process and use MoisesDB. Alongside a thorough documentation and analysis of the dataset contents, this work provides baseline results for open-source separation models for varying separation granularities (four, five, and six stems), and discuss their results.

Key facts. Cited by 39 papers in the map (data through 14 Oct 2026). Builds on 5 of its 23 references that are in the map. First posted on arXiv 29 Jul 2023.

Builds on

5 of 23 references.

References · 5

  1. 2022Hybrid Transformers for Music Source Separationcited by 134
  2. 2019Cutting Music Source Separation Some Slakh: A Dataset to Study the Impact of Training Data Quality and Quantitycited by 86
  3. 2021Decoupling Magnitude and Phase Estimation with Deep ResUNet for Music Source Separationcited by 48
  4. 2019Singing voice separation: a study on training datacited by 5
  5. 2022Towards robust music source separation on loud commercial musiccited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 8; 2025: 12; 2026: 17.

39 papers.

Sort:

By area:

  1. 2023AudioSR: Versatile Audio Super-resolution at Scalecited by 39
  2. 2024Instruct-MusicGen: Unlocking Text-to-Music Editing for Music Language Models via Instruction Tuningcited by 15
  3. 2024COCOLA: Coherence-Oriented Contrastive Learning of Musical Audio Representationscited by 14
  4. 2025A Comprehensive Real-World Assessment of Audio Watermarking Algorithms: Will They Survive Neural Codecs?cited by 13
  5. 2024Apollo: Band-sequence Modeling for High-Quality Audio Restorationcited by 8
  6. 2024A Stem-Agnostic Single-Decoder System for Music Source Separation Beyond Four Stemscited by 7
  7. 2025UniFlow-Audio: Unified Flow Matching for Audio Generation from Omni-Modalitiescited by 6
  8. 2025FlashSR: One-step Versatile Audio Super-resolution via Diffusion Distillationcited by 5
  9. 2025Music Source Restorationcited by 5
  10. 2025MGE-LDM: Joint Latent Diffusion for Simultaneous Music Generation and Source Extractioncited by 4
  11. 2023The ICASSP SP Cadenza Challenge: Music Demixing/Remixing for Hearing Aidscited by 3
  12. 2025UniverSR: Unified and Versatile Audio Super-Resolution via Vocoder-Free Flow Matchingcited by 3
27 more
  1. 2025User-guided Generative Source Separationcited by 2
  2. 2025AnyAccomp: Generalizable Accompaniment Generation via Quantized Melodic Bottleneckcited by 2
  3. 2026DARC: Drum accompaniment generation with fine-grained rhythm controlcited by 2
  4. 2024The first Cadenza challenges: using machine learning competitions to improve music for listeners with a hearing losscited by 1
  5. 2024An Ensemble Approach to Music Source Separation: A Comparative Analysis of Conventional and Hierarchical Stem Separationcited by 1
  6. 2025Learning Linearity in Audio Consistency Autoencoders via Implicit Regularizationcited by 1
  7. 2026Summary of The Inaugural Music Source Restoration Challengecited by 1
  8. 2026Stemphonic: All-at-once Flexible Multi-stem Music Generationcited by 1
  9. 2024Facing the Music: Tackling Singing Voice Separation in Cinematic Audio Source Separationcited by 0
  10. 2024Zero-shot Musical Stem Retrieval with Joint-Embedding Predictive Architecturescited by 0
  11. 2025Audio-FLAN: An Instruction-Following Dataset for Unified Audio Understanding and Generation of Speech, Music, and Soundcited by 0
  12. 2025Learning Relationships Between Separate Audio Tracks for Creative Applicationscited by 0
  13. 2025A Conditioned UNet for Music Source Separationcited by 0
  14. 2026PF-D2M: A Pose-free Diffusion Model for Universal Dance-to-Music Generationcited by 0
  15. 2026Multi-Stage Music Source Restoration with BandSplit-RoFormer Separation and HiFi++ GANcited by 0
  16. 2026Diff-VS: Efficient Audio-Aware Diffusion U-Net for Vocals Separationcited by 0
  17. 2026A Cold Diffusion Approach for Percussive Dereverberationcited by 0
  18. 2026Elastic Time: Dynamic Frame Rate Bottlenecks for Neural Audio Codingcited by 0
  19. 2026Music-Source-Separation-Training (MSST): A Unified Framework for Training and Evaluating Music Demixing Modelscited by 0
  20. 2026Diff2Mix: Controllable Music Mixing via Diffusion Models and Differentiable Audio Effectscited by 0
  21. 2026How Much AI Is in This Track? Quantifying the Proportion of AI-Generated Stems in Hybrid Music Mixturescited by 0
  22. 2026Iterative Audio Separation with Mixture Consistency via MIMO Model Extensioncited by 0
  23. 2026AURA: Unified Multimodal Framework for Conversational Music Editingcited by 0
  24. 2026Don't CLAP: Are Music-Text Models Bag-of-Words?cited by 0
  25. 2026Open-Qwen-Music: An Auditable Framework for LLM-Based Music Composition and Diffusion Renderingcited by 0
  26. 2026SAGE: Semantic Audio Generative Encodercited by 0
  27. 2026JazzSAMBA: A Synchronous and Asynchronous Multi-take Band Audio Dataset of Jazz Standards for Live Music Modelscited by 0