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

• URL: http://arxiv.org/abs/2603.09187v1
• Date: Tue, 10 Mar 2026 04:54:53 GMT
• Title: The Costs of Reproducibility in Music Separation Research: a Replication of Band-Split RNN
• Abstract summary: 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.<n>Unfortunately, it is not straightforward to reproduce since its full code is not available.<n>This paper attempts to replicate BSRNN as closely as possible to the original paper through extensive experiments.
• Score: 24.79659407567392
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• On the Learning Dynamics of RLVR at the Edge of Competence [86.52481827737097]
  Reinforcement learning with verifiable rewards (RLVR) has been a main driver of recent breakthroughs in large reasoning models.<n>We develop a theory of the training dynamics of RL for transformers on compositional reasoning tasks.
  arXiv  Detail & Related papers  (2026-02-16T16:03:08Z)
• Automatic Classification of User Requirements from Online Feedback -- A Replication Study [0.0]
  We replicate a previous NLP4RE study (baseline), which evaluated different deep learning models for requirement classification from user reviews.<n>We reproduced the original results using publicly released source code, thereby helping to strengthen the external validity of the baseline study.<n>Our findings revealed that baseline deep learning models, BERT and ELMo, exhibited good capabilities on an external dataset, and GPT-4o showed performance comparable to traditional baseline machine learning models.
  arXiv  Detail & Related papers  (2025-07-29T06:52:27Z)
• 100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models [58.98176123850354]
  The recent release of DeepSeek-R1 has generated widespread social impact and sparked enthusiasm in the research community for exploring the explicit reasoning paradigm of language models.<n>The implementation details of the released models have not been fully open-sourced by DeepSeek, including DeepSeek-R1-Zero, DeepSeek-R1, and the distilled small models.<n>Many replication studies have emerged aiming to reproduce the strong performance achieved by DeepSeek-R1, reaching comparable performance through similar training procedures and fully open-source data resources.
  arXiv  Detail & Related papers  (2025-05-01T14:28:35Z)
• Concise Reasoning via Reinforcement Learning [13.657506042120167]
  We revisit the core principles of reinforcement learning (RL)<n>We uncover a natural correlation between conciseness and accuracy that has been largely overlooked.<n>We show that introducing a secondary phase of RL training, using a very small set of problems, can significantly reduce chains of thought.
  arXiv  Detail & Related papers  (2025-04-07T15:35:54Z)
• Reusing Embeddings: Reproducible Reward Model Research in Large Language Model Alignment without GPUs [58.18140409409302]
  Large Language Models (LLMs) have made substantial strides in structured tasks through Reinforcement Learning (RL)<n>Applying RL in broader domains like chatbots and content generation presents unique challenges.<n>We show a case study of reproducing existing reward model ensemble research using embedding-based reward models.
  arXiv  Detail & Related papers  (2025-02-04T19:37:35Z)
• Noisy Self-Training with Synthetic Queries for Dense Retrieval [49.49928764695172]
  We introduce a novel noisy self-training framework combined with synthetic queries. Experimental results show that our method improves consistently over existing methods. Our method is data efficient and outperforms competitive baselines.
  arXiv  Detail & Related papers  (2023-11-27T06:19:50Z)
• Self-Supervised Contrastive Learning for Robust Audio-Sheet Music Retrieval Systems [3.997809845676912]
  We show that self-supervised contrastive learning can mitigate the scarcity of annotated data from real music content. We employ the snippet embeddings in the higher-level task of cross-modal piece identification. In this work, we observe that the retrieval quality improves from 30% up to 100% when real music data is present.
  arXiv  Detail & Related papers  (2023-09-21T14:54:48Z)
• ReDi: Efficient Learning-Free Diffusion Inference via Trajectory Retrieval [68.7008281316644]
  ReDi is a learning-free Retrieval-based Diffusion sampling framework. We show that ReDi improves the model inference efficiency by 2x speedup.
  arXiv  Detail & Related papers  (2023-02-05T03:01:28Z)
• DeepZensols: Deep Natural Language Processing Framework [23.56171046067646]
  This work is a framework that is able to reproduce consistent results. It provides a means of easily creating, training, and evaluating natural language processing (NLP) deep learning (DL) models.
  arXiv  Detail & Related papers  (2021-09-08T01:16:05Z)
• Research Reproducibility as a Survival Analysis [22.66983713481359]
  We consider modeling a paper as a survival analysis problem. We show how a survival analysis allows us to draw new insights that better explain prior longitudinal data.
  arXiv  Detail & Related papers  (2020-12-17T20:56:53Z)
• Offline Reinforcement Learning Hands-On [60.36729294485601]
  offline RL aims to turn large datasets into powerful decision-making engines without any online interactions with the environment. This work aims to reflect upon these efforts from a practitioner viewpoint. We experimentally validate that diversity and high-return examples in the data are crucial to the success of offline RL.
  arXiv  Detail & Related papers  (2020-11-29T14:45:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.