Summary of The Inaugural Music Source Restoration Challenge

• URL: http://arxiv.org/abs/2601.04343v1
• Date: Wed, 07 Jan 2026 19:31:06 GMT
• Title: Summary of The Inaugural Music Source Restoration Challenge
• Abstract summary: Music Source Restoration (MSR) aims to recover original, unprocessed instrument stems from professionally mixed audio.<n>MSR Challenge features objective evaluation on studio-produced mixtures using Multi-Mel-SNR, Zimtohrli, and FAD-CLAP.<n>Winning system achieved 4.46 dB Multi-Mel-SNR and 3.47 MOS-Overall, corresponding to relative improvements of 91% and 18% over the second-place system, respectively.
• Score: 52.405241781545634
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Music Source Restoration (MSR) aims to recover original, unprocessed instrument stems from professionally mixed and degraded audio, requiring the reversal of both production effects and real-world degradations. We present the inaugural MSR Challenge, which features objective evaluation on studio-produced mixtures using Multi-Mel-SNR, Zimtohrli, and FAD-CLAP, alongside subjective evaluation on real-world degraded recordings. Five teams participated in the challenge. The winning system achieved 4.46 dB Multi-Mel-SNR and 3.47 MOS-Overall, corresponding to relative improvements of 91% and 18% over the second-place system, respectively. Per-stem analysis reveals substantial variation in restoration difficulty across instruments, with bass averaging 4.59 dB across all teams, while percussion averages only 0.29 dB. The dataset, evaluation protocols, and baselines are available at https://msrchallenge.com/.

Related papers

• MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation [88.7702943548674]
  We introduce MSAVBench, the first comprehensive benchmark and adaptive hybrid evaluation framework for multi-shot audio-video generation.<n>Our benchmark spans four key dimensions, video, audio, shot, and reference, covering diverse task settings, varying shot counts of up to 15, and challenging non-realistic scenarios.<n> MSAVBench achieves high alignment with human judgments, reaching a Spearman rank correlation of 91.5%.
  arXiv  Detail & Related papers  (2026-05-19T17:59:33Z)
• Byte-Exact Deduplication in Retrieval-Augmented Generation: A Three-Regime Empirical Analysis Across Public Benchmarks [0.0]
  Preprint presents an empirical analysis of byte-exact chunk-level deduplication in Retrieval-Augmented Generation (RAG) pipelines.<n>We measure context reduction across three distinct operating regimes: clean academic retrieval, constructed enterprisevendor patterns, and multi-turn conversational AI.<n>All four vendors clear the strict 5% Wilson 95% upper-bound MAT threshold in both the clean and high-redundancy RAG regimes.
  arXiv  Detail & Related papers  (2026-05-10T15:48:38Z)
• Music Source Restoration with Ensemble Separation and Targeted Reconstruction [6.528712884168779]
  The Inaugural Music Source Restoration (MSR) Challenge targets the recovery of original, unprocessed stems from fully mixed and mastered music.<n>To address MSR, we propose a two-stage system. First, an ensemble of pre-trained separation models produces preliminary source estimates.<n>Then a set of pre-trained BSRNN-based restoration models performs targeted reconstruction to refine these estimates.
  arXiv  Detail & Related papers  (2026-03-13T07:40:42Z)
• Multi-Stage Music Source Restoration with BandSplit-RoFormer Separation and HiFi++ GAN [8.647179779228761]
  Music Source Restoration (MSR) targets recovery of original, unprocessed instrument stems from fully mixed and mastered audio.<n>This technical report presents the CP-JKU team's system for the MSR ICASSP Challenge 2025.
  arXiv  Detail & Related papers  (2026-03-04T13:10:39Z)
• MMMOS: Multi-domain Multi-axis Audio Quality Assessment [49.48516314472825]
  Existing non-intrusive assessment models predict a single Mean Opinion Score (MOS) for speech.<n>We propose MMMOS, a no-reference, multi-domain audio quality assessment system that estimates four axes: Production Quality, Production Complexity, Content Enjoyment, and Content Usefulness.<n> MMMOS shows a 20-30% reduction in mean squared error and a 4-5% increase in Kendall's tau versus baseline.
  arXiv  Detail & Related papers  (2025-07-05T16:42:09Z)
• Music Source Restoration [20.814486236405823]
  We introduce Music Source Restoration (MSR), a novel task addressing the gap between idealized source separation and real-world music production.<n>MSR models mixtures as degraded sums of individually degraded sources, with the goal of recovering original, undegraded signals.<n>Due to the lack of data for MSR, we present RawStems, a dataset annotation of 578 songs with unprocessed source signals organized into 8 primary and 17 secondary instrument groups, totaling 354.13 hours.
  arXiv  Detail & Related papers  (2025-05-27T23:27:31Z)
• Remedy: Learning Machine Translation Evaluation from Human Preferences with Reward Modeling [4.548755617115687]
  We propose ReMedy, a novel MT metric framework that reformulates translation evaluation as a reward modeling task.<n>Instead of regressing on imperfect human ratings directly, ReMedy learns relative translation quality using pairwise preference data.<n>In extensive experiments across WMT22-24 shared tasks, ReMedy achieves state-of-the-art performance at both segment- and system-level evaluation.
  arXiv  Detail & Related papers  (2025-04-18T11:11:14Z)
• Aligning Text-to-Music Evaluation with Human Preferences [63.08368388389259]
  We study the design space of reference-based divergence metrics for evaluating generative acoustic text-to-music (TTM) models.<n>We find that not only is the standard FAD setup inconsistent on both synthetic and human preference data, but that nearly all existing metrics fail to effectively capture desiderata.<n>We propose a new metric, the MAUVE Audio Divergence (MAD), computed on representations from a self-supervised audio embedding model.
  arXiv  Detail & Related papers  (2025-03-20T19:31:04Z)
• An Early FIRST Reproduction and Improvements to Single-Token Decoding for Fast Listwise Reranking [50.81324768683995]
  FIRST is a novel approach that integrates a learning-to-rank objective and leveraging the logits of only the first generated token. We extend the evaluation of FIRST to the TREC Deep Learning datasets (DL19-22), validating its robustness across diverse domains. Our experiments confirm that fast reranking with single-token logits does not compromise out-of-domain reranking quality.
  arXiv  Detail & Related papers  (2024-11-08T12:08:17Z)
• MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning [80.15393178083607]
  Large Language Models' (LLM) reasoning can be improved using test-time aggregation strategies, i.e., generating multiple samples and voting among generated samples.<n> Refinement offers an alternative by using LLM-generated feedback to improve solution quality.<n>We propose MAgICoRe, which avoids excessive refinement by categorizing problem difficulty as easy or hard.
  arXiv  Detail & Related papers  (2024-09-18T17:12:41Z)
• D4AM: A General Denoising Framework for Downstream Acoustic Models [45.04967351760919]
  Speech enhancement (SE) can be used as a front-end strategy to aid automatic speech recognition (ASR) systems. Existing training objectives of SE methods are not fully effective at integrating speech-text and noisy-clean paired data for training toward unseen ASR systems. We propose a general denoising framework, D4AM, for various downstream acoustic models.
  arXiv  Detail & Related papers  (2023-11-28T08:27:27Z)
• Blind Restoration of Real-World Audio by 1D Operational GANs [18.462912387382346]
  We propose a novel approach for blind restoration of real-world audio signals by Operational Generative Adversarial Networks (Op-GANs) The proposed approach has been evaluated extensively over the benchmark TIMIT-RAR (speech) and GTZAN-RAR (non-speech) datasets. Average SDR improvements of over 7.2 dB and 4.9 dB are achieved, respectively, which are substantial when compared with the baseline methods.
  arXiv  Detail & Related papers  (2022-12-30T10:11:57Z)
• Hybrid Spectrogram and Waveform Source Separation [91.3755431537592]
  We show how to perform end-to-end hybrid source separation, letting the model decide which domain is best suited for each source. The proposed hybrid version of the Demucs architecture won the Music Demixing Challenge 2021 organized by Sony.
  arXiv  Detail & Related papers  (2021-11-05T16:37:45Z)

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.