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

• URL: http://arxiv.org/abs/2607.23395v1
• Date: Sat, 25 Jul 2026 23:43:19 GMT
• Title: Music-Source-Separation-Training (MSST): A Unified Framework for Training and Evaluating Music Demixing Models
• Abstract summary: Music Source Separation (MSS) is central to applications ranging from karaoke and remixing to audio restoration and content production.<n>This paper presents MSST (Music-Source-Separation-Training) - a universal open-source framework for MSS tasks.
• Score: 39.3098730337656
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: 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.

Related papers

• AVRT: Audio-Visual Reasoning Transfer through Single-Modality Teachers [51.016506778535025]
  We develop a framework that generates high-quality audio-visual reasoning traces from single-modality teacher models.<n>We show that cross-modal training also transfers to single-modality tasks.
  arXiv  Detail & Related papers  (2026-04-17T18:13:27Z)
• High-Quality Sound Separation Across Diverse Categories via Visually-Guided Generative Modeling [65.02357548201188]
  We propose DAVIS, a Diffusion-based Audio-VIsual Separation framework that solves the audio-visual sound source separation task through generative learning.<n>Our framework operates by synthesizing the desired separated sound spectrograms directly from a noise distribution, conditioned concurrently on the mixed audio input and associated visual information.
  arXiv  Detail & Related papers  (2025-09-26T08:46:00Z)
• Frequency-Domain Decomposition and Recomposition for Robust Audio-Visual Segmentation [60.9960601057956]
  We introduce Frequency-Aware Audio-Visualcomposer (FAVS) framework consisting of two key modules.<n>FAVS framework achieves state-of-the-art performance on three benchmark datasets.
  arXiv  Detail & Related papers  (2025-09-23T12:33:48Z)
• TISDiSS: A Training-Time and Inference-Time Scalable Framework for Discriminative Source Separation [7.238310342477333]
  We propose Training-Time and Inference-Time Scalable Discriminative Source Separation (TISDiSS)<n>TISDiSS integrates early-split multi-loss supervision, shared- parameter design, and dynamic inference repetitions.<n> Experiments on standard speech separation benchmarks demonstrate state-of-the-art performance with a reduced parameter count.
  arXiv  Detail & Related papers  (2025-09-19T06:42:27Z)
• Intrinsic Training Signals for Federated Learning Aggregation [13.540945877050525]
  Federated Learning (FL) enables collaborative model training across distributed clients while preserving data privacy.<n>This work demonstrates that effective model merging can be achieved solely through existing training signals.
  arXiv  Detail & Related papers  (2025-07-09T13:03:23Z)
• Episode-specific Fine-tuning for Metric-based Few-shot Learners with Optimization-based Training [13.5196633635749]
  Metric-based models operate by computing similarities between query and support embeddings within a learned metric space.<n>A small set of labeled support samples is provided during inference to aid the classification of unlabeled query samples.<n>We propose a series of simple yet effective episode-specific, during-inference fine-tuning methods for metric-based models.
  arXiv  Detail & Related papers  (2025-06-20T22:24:38Z)
• Memory-guided Network with Uncertainty-based Feature Augmentation for Few-shot Semantic Segmentation [12.653336728447654]
  We propose a class-shared memory (CSM) module consisting of a set of learnable memory vectors. These memory vectors learn elemental object patterns from base classes during training whilst re-encoding query features during both training and inference. We integrate CSM and UFA into representative FSS works, with experimental results on the widely-used PASCAL-5$i$ and COCO-20$i$ datasets.
  arXiv  Detail & Related papers  (2024-06-01T19:53:25Z)
• Multimodal Imbalance-Aware Gradient Modulation for Weakly-supervised Audio-Visual Video Parsing [107.031903351176]
  Weakly-separated audio-visual video parsing (WS-AVVP) aims to localize the temporal extents of audio, visual and audio-visual event instances. WS-AVVP aims to identify the corresponding event categories with only video-level category labels for training.
  arXiv  Detail & Related papers  (2023-07-05T05:55:10Z)
• Switchable Representation Learning Framework with Self-compatibility [50.48336074436792]
  We propose a Switchable representation learning Framework with Self-Compatibility (SFSC) SFSC generates a series of compatible sub-models with different capacities through one training process. SFSC achieves state-of-the-art performance on the evaluated datasets.
  arXiv  Detail & Related papers  (2022-06-16T16:46:32Z)

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.