# Music-Source-Separation-Training (MSST): A Unified Framework for Training and Evaluating Music Demixing Models

arXiv: https://arxiv.org/abs/2607.23395 · HTML: https://mlsanity.com/paper/2607.23395/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 43 references that are in the map.
- First posted on arXiv 25 Jul 2026.

## Builds on (most cited first, 21 of 21)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [On the Variance of the Adaptive Learning Rate and Beyond](https://mlsanity.com/paper/1908.03265/) (2019)
- [SDR - half-baked or well done?](https://mlsanity.com/paper/1811.02508/) (2018)
- [8-bit Optimizers via Block-wise Quantization](https://mlsanity.com/paper/2110.02861/) (2021)
- [Hybrid Transformers for Music Source Separation](https://mlsanity.com/paper/2211.08553/) (2022)
- [Prodigy: An Expeditiously Adaptive Parameter-Free Learner](https://mlsanity.com/paper/2306.06101/) (2023)
- [Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation](https://mlsanity.com/paper/1806.03185/) (2018)
- [Music Source Separation in the Waveform Domain](https://mlsanity.com/paper/1911.13254/) (2019)
- [Hybrid Spectrogram and Waveform Source Separation](https://mlsanity.com/paper/2111.03600/) (2021)
- [Decoupling Magnitude and Phase Estimation with Deep ResUNet for Music Source Separation](https://mlsanity.com/paper/2109.05418/) (2021)
- [Asteroid: the PyTorch-based audio source separation toolkit for researchers](https://mlsanity.com/paper/2005.04132/) (2020)
- [Moisesdb: A dataset for source separation beyond 4-stems](https://mlsanity.com/paper/2307.15913/) (2023)
- [Music Demixing Challenge 2021](https://mlsanity.com/paper/2108.13559/) (2021)
- [Music Source Separation with Band-Split RoPE Transformer](https://mlsanity.com/paper/2309.02612/) (2023)
- [KUIELab-MDX-Net: A Two-Stream Neural Network for Music Demixing](https://mlsanity.com/paper/2111.12203/) (2021)
- [The Sound Demixing Challenge 2023 unicodex2013 Music Demixing Track](https://mlsanity.com/paper/2308.06979/) (2023)
- [On loss functions and evaluation metrics for music source separation](https://mlsanity.com/paper/2202.07968/) (2022)
- [Mel-Band RoFormer for Music Source Separation](https://mlsanity.com/paper/2310.01809/) (2023)
- [SCNet: Sparse Compression Network for Music Source Separation](https://mlsanity.com/paper/2401.13276/) (2024)

## Abstract (arXiv)

Music Source Separation (MSS), the task of recovering individual sound components (stems) from a polyphonic mixture, is central to applications ranging from karaoke and remixing to audio restoration and content production. The separation quality depends on engineering decisions across the entire pipeline: model choice, training data preparation and augmentation, loss function and metrics choice, training configuration, validation, and post-processing. This paper presents MSST (Music-Source-Separation-Training) - a universal open-source framework for MSS tasks, which unifies training, validation, and inference for a broad range of modern demixing model families under a single, configuration-driven interface. The framework supports various model architectures, data preprocessing and augmentations, multiple loss functions and evaluation metrics, which helps with fast iterations and ablation studies. Additionally, the framework supports a range of practical techniques that improve separation quality, such as sliding-window inference with cross-fading, test-time augmentation, model ensembling, and fine-tuning via Low-Rank Adaptation (LORA). Our ablation studies demonstrate improvements of MSS using the above techniques. By consolidating these components into a reproducible, YAML-configurable framework, MSST lowers the barrier to systematic experimentation and enables rapid iteration from idea to verifiable result.