# The Costs of Reproducibility in Music Separation Research: a Replication of Band-Split RNN

arXiv: https://arxiv.org/abs/2603.09187 · HTML: https://mlsanity.com/paper/2603.09187/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 62 references that are in the map.
- First posted on arXiv 10 Mar 2026.

## Builds on (most cited first, 30 of 33)

- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning](https://mlsanity.com/paper/2002.05651/) (2020)
- [Accounting for Variance in Machine Learning Benchmarks](https://mlsanity.com/paper/2103.03098/) (2021)
- [Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches](https://mlsanity.com/paper/1907.06902/) (2019)
- [Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation](https://mlsanity.com/paper/1910.06379/) (2019)
- [Hybrid Transformers for Music Source Separation](https://mlsanity.com/paper/2211.08553/) (2022)
- [Hybrid Spectrogram and Waveform Source Separation](https://mlsanity.com/paper/2111.03600/) (2021)
- [Music Source Separation with Band-split RNN](https://mlsanity.com/paper/2209.15174/) (2022)
- [Decoupling Magnitude and Phase Estimation with Deep ResUNet for Music Source Separation](https://mlsanity.com/paper/2109.05418/) (2021)
- [TF-GridNet: Making Time-Frequency Domain Models Great Again for Monaural Speaker Separation](https://mlsanity.com/paper/2209.03952/) (2022)
- [The 2018 Signal Separation Evaluation Campaign](https://mlsanity.com/paper/1804.06267/) (2018)
- [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)
- [Differentiable Consistency Constraints for Improved Deep Speech Enhancement](https://mlsanity.com/paper/1811.08521/) (2018)
- [A Systematic Review of Reproducibility Research in Natural Language Processing](https://mlsanity.com/paper/2103.07929/) (2021)
- [D3Net: Densely connected multidilated DenseNet for music source separation](https://mlsanity.com/paper/2010.01733/) (2020)
- [KUIELab-MDX-Net: A Two-Stream Neural Network for Music Demixing](https://mlsanity.com/paper/2111.12203/) (2021)
- [All for One and One for All: Improving Music Separation by Bridging Networks](https://mlsanity.com/paper/2010.04228/) (2020)
- [The Sound Demixing Challenge 2023 unicodex2013 Music Demixing Track](https://mlsanity.com/paper/2308.06979/) (2023)
- [A Unified Model for Zero-shot Music Source Separation, Transcription and Synthesis](https://mlsanity.com/paper/2108.03456/) (2021)
- [Dense CNN with Self-Attention for Time-Domain Speech Enhancement](https://mlsanity.com/paper/2009.01941/) (2020)
- [High Fidelity Speech Enhancement with Band-split RNN](https://mlsanity.com/paper/2212.00406/) (2022)
- [We need to talk about random seeds](https://mlsanity.com/paper/2210.13393/) (2022)
- [Demystifying TasNet: A Dissecting Approach](https://mlsanity.com/paper/1911.08895/) (2019)
- [Music Source Separation Based on a Lightweight Deep Learning Framework (DTTNET: DUAL-PATH TFC-TDF UNET)](https://mlsanity.com/paper/2309.08684/) (2023)
- [ESPnet-ST-v2: Multipurpose Spoken Language Translation Toolkit](https://mlsanity.com/paper/2304.04596/) (2023)
- [CWS-PResUNet: Music Source Separation with Channel-wise Subband Phase-aware ResUNet](https://mlsanity.com/paper/2112.04685/) (2021)
- [A Generalized Bandsplit Neural Network for Cinematic Audio Source Separation](https://mlsanity.com/paper/2309.02539/) (2023)
- [Why does music source separation benefit from cacophony?](https://mlsanity.com/paper/2402.18407/) (2024)
- [MaD TwinNet: Masker-Denoiser Architecture with Twin Networks for Monaural Sound Source Separation](https://mlsanity.com/paper/1802.00300/) (2018)

## Abstract (arXiv)

Music source separation is the task of isolating the instrumental tracks from a music song. Despite its spectacular recent progress, the trend towards more complex architectures and training protocols exacerbates reproducibility issues. The band-split recurrent neural networks (BSRNN) model is promising in this regard, since it yields close to state-of-the-art results on public datasets, and requires reasonable resources for training. Unfortunately, it is not straightforward to reproduce since its full code is not available. In this paper, we attempt to replicate BSRNN as closely as possible to the original paper through extensive experiments, which allows us to conduct a critical reflection on this reproducibility issue. Our contributions are three-fold. First, this study yields several insights on the model design and training pipeline, which sheds light on potential future improvements. In particular, since we were unsuccessful in reproducing the original results, we explore additional variants that ultimately yield an optimized BSRNN model, whose performance largely improves that of the original. Second, we discuss reproducibility issues from both methodological and practical perspectives. We notably underline how substantial time and energy costs could have been saved upon availability of the full pipeline. Third, our code and pre-trained models are released publicly to foster reproducible research. We hope that this study will contribute to spread awareness on the importance of reproducible research in the music separation community, and help promoting more transparent and sustainable practices.