# Moisesdb: A dataset for source separation beyond 4-stems

arXiv: https://arxiv.org/abs/2307.15913 · HTML: https://mlsanity.com/paper/2307.15913/

## 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 (most cited first, 5 of 5)

- [Hybrid Transformers for Music Source Separation](https://mlsanity.com/paper/2211.08553/) (2022)
- [Cutting Music Source Separation Some Slakh: A Dataset to Study the Impact of Training Data Quality and Quantity](https://mlsanity.com/paper/1909.08494/) (2019)
- [Decoupling Magnitude and Phase Estimation with Deep ResUNet for Music Source Separation](https://mlsanity.com/paper/2109.05418/) (2021)
- [Singing voice separation: a study on training data](https://mlsanity.com/paper/1906.02618/) (2019)
- [Towards robust music source separation on loud commercial music](https://mlsanity.com/paper/2208.14355/) (2022)

## Built on by (most cited first, 30 of 39)

- [AudioSR: Versatile Audio Super-resolution at Scale](https://mlsanity.com/paper/2309.07314/) (2023)
- [Instruct-MusicGen: Unlocking Text-to-Music Editing for Music Language Models via Instruction Tuning](https://mlsanity.com/paper/2405.18386/) (2024)
- [COCOLA: Coherence-Oriented Contrastive Learning of Musical Audio Representations](https://mlsanity.com/paper/2404.16969/) (2024)
- [A Comprehensive Real-World Assessment of Audio Watermarking Algorithms: Will They Survive Neural Codecs?](https://mlsanity.com/paper/2505.19663/) (2025)
- [Apollo: Band-sequence Modeling for High-Quality Audio Restoration](https://mlsanity.com/paper/2409.08514/) (2024)
- [A Stem-Agnostic Single-Decoder System for Music Source Separation Beyond Four Stems](https://mlsanity.com/paper/2406.18747/) (2024)
- [UniFlow-Audio: Unified Flow Matching for Audio Generation from Omni-Modalities](https://mlsanity.com/paper/2509.24391/) (2025)
- [FlashSR: One-step Versatile Audio Super-resolution via Diffusion Distillation](https://mlsanity.com/paper/2501.10807/) (2025)
- [Music Source Restoration](https://mlsanity.com/paper/2505.21827/) (2025)
- [MGE-LDM: Joint Latent Diffusion for Simultaneous Music Generation and Source Extraction](https://mlsanity.com/paper/2505.23305/) (2025)
- [The ICASSP SP Cadenza Challenge: Music Demixing/Remixing for Hearing Aids](https://mlsanity.com/paper/2310.03480/) (2023)
- [UniverSR: Unified and Versatile Audio Super-Resolution via Vocoder-Free Flow Matching](https://mlsanity.com/paper/2510.00771/) (2025)
- [User-guided Generative Source Separation](https://mlsanity.com/paper/2507.01339/) (2025)
- [AnyAccomp: Generalizable Accompaniment Generation via Quantized Melodic Bottleneck](https://mlsanity.com/paper/2509.14052/) (2025)
- [DARC: Drum accompaniment generation with fine-grained rhythm control](https://mlsanity.com/paper/2601.02357/) (2026)
- [The first Cadenza challenges: using machine learning competitions to improve music for listeners with a hearing loss](https://mlsanity.com/paper/2409.05095/) (2024)
- [An Ensemble Approach to Music Source Separation: A Comparative Analysis of Conventional and Hierarchical Stem Separation](https://mlsanity.com/paper/2410.20773/) (2024)
- [Learning Linearity in Audio Consistency Autoencoders via Implicit Regularization](https://mlsanity.com/paper/2510.23530/) (2025)
- [Summary of The Inaugural Music Source Restoration Challenge](https://mlsanity.com/paper/2601.04343/) (2026)
- [Stemphonic: All-at-once Flexible Multi-stem Music Generation](https://mlsanity.com/paper/2602.09891/) (2026)
- [Facing the Music: Tackling Singing Voice Separation in Cinematic Audio Source Separation](https://mlsanity.com/paper/2408.03588/) (2024)
- [Zero-shot Musical Stem Retrieval with Joint-Embedding Predictive Architectures](https://mlsanity.com/paper/2411.19806/) (2024)
- [Audio-FLAN: An Instruction-Following Dataset for Unified Audio Understanding and Generation of Speech, Music, and Sound](https://mlsanity.com/paper/2502.16584/) (2025)
- [Learning Relationships Between Separate Audio Tracks for Creative Applications](https://mlsanity.com/paper/2509.25296/) (2025)
- [A Conditioned UNet for Music Source Separation](https://mlsanity.com/paper/2512.15532/) (2025)
- [PF-D2M: A Pose-free Diffusion Model for Universal Dance-to-Music Generation](https://mlsanity.com/paper/2601.15872/) (2026)
- [Multi-Stage Music Source Restoration with BandSplit-RoFormer Separation and HiFi++ GAN](https://mlsanity.com/paper/2603.04032/) (2026)
- [Diff-VS: Efficient Audio-Aware Diffusion U-Net for Vocals Separation](https://mlsanity.com/paper/2604.01120/) (2026)
- [A Cold Diffusion Approach for Percussive Dereverberation](https://mlsanity.com/paper/2605.10256/) (2026)
- [Elastic Time: Dynamic Frame Rate Bottlenecks for Neural Audio Coding](https://mlsanity.com/paper/2606.27320/) (2026)

## 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.