Training-Free Multi-Step Audio Source Separation

• URL: http://arxiv.org/abs/2505.19534v1
• Date: Mon, 26 May 2025 05:40:12 GMT
• Title: Training-Free Multi-Step Audio Source Separation
• Authors: Yongyi Zang, Jingyi Li, Qiuqiang Kong,
• Abstract summary: We show that pretrained one-step audio source separation models can be leveraged for multi-step separation without additional training.<n>We propose a simple yet effective inference method that iteratively applies separation by optimally blending the input mixture with the previous step's separation result.<n>Our empirical results demonstrate that our multi-step separation approach consistently outperforms one-step inference across both speech enhancement and music source separation tasks.
• Score: 16.187944473839632
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Audio source separation aims to separate a mixture into target sources. Previous audio source separation systems usually conduct one-step inference, which does not fully explore the separation ability of models. In this work, we reveal that pretrained one-step audio source separation models can be leveraged for multi-step separation without additional training. We propose a simple yet effective inference method that iteratively applies separation by optimally blending the input mixture with the previous step's separation result. At each step, we determine the optimal blending ratio by maximizing a metric. We prove that our method always yield improvement over one-step inference, provide error bounds based on model smoothness and metric robustness, and provide theoretical analysis connecting our method to denoising along linear interpolation paths between noise and clean distributions, a property we link to denoising diffusion bridge models. Our approach effectively delivers improved separation performance as a "free lunch" from existing models. Our empirical results demonstrate that our multi-step separation approach consistently outperforms one-step inference across both speech enhancement and music source separation tasks, and can achieve scaling performance similar to training a larger model, using more data, or in some cases employing a multi-step training objective. These improvements appear not only on the optimization metric during multi-step inference, but also extend to nearly all non-optimized metrics (with one exception). We also discuss limitations of our approach and directions for future research.

Related papers

• Improving Multimodal Learning Balance and Sufficiency through Data Remixing [14.282792733217653]
  Methods for enforcing the weak modality fail to achieve unimodal sufficiency and multimodal balance.<n>We propose multimodal Data Remixing, including decoupling multimodal data and filtering hard samples for each modality to mitigate modality imbalance.<n>Our method can be seamlessly integrated with existing approaches, improving accuracy by approximately 6.50%$uparrow$ on CREMAD and 3.41%$uparrow$ on Kinetic-Sounds.
  arXiv  Detail & Related papers  (2025-06-13T08:01:29Z)
• Training-free Diffusion Model Alignment with Sampling Demons [15.400553977713914]
  We propose an optimization approach, dubbed Demon, to guide the denoising process at inference time without backpropagation through reward functions or model retraining.<n>Our approach works by controlling noise distribution in denoising steps to concentrate density on regions corresponding to high rewards through optimization.<n>Our experiments show that the proposed approach significantly improves the average aesthetics scores text-to-image generation.
  arXiv  Detail & Related papers  (2024-10-08T07:33:49Z)
• MMDisCo: Multi-Modal Discriminator-Guided Cooperative Diffusion for Joint Audio and Video Generation [15.29891397291197]
  This study aims to construct an audio-video generative model with minimal computational cost.<n>We propose a novel method that guides single-modal models to cooperatively generate well-aligned samples across modalities.<n> Empirical evaluations on several benchmark datasets demonstrate that our method improves both single-modal fidelity and multimodal alignment with relatively few parameters.
  arXiv  Detail & Related papers  (2024-05-28T05:43:03Z)
• Multi-scale Diffusion Denoised Smoothing [79.95360025953931]
  randomized smoothing has become one of a few tangible approaches that offers adversarial robustness to models at scale. We present scalable methods to address the current trade-off between certified robustness and accuracy in denoised smoothing. Our experiments show that the proposed multi-scale smoothing scheme combined with diffusion fine-tuning enables strong certified robustness available with high noise level.
  arXiv  Detail & Related papers  (2023-10-25T17:11:21Z)
• Score-based Source Separation with Applications to Digital Communication Signals [72.6570125649502]
  We propose a new method for separating superimposed sources using diffusion-based generative models. Motivated by applications in radio-frequency (RF) systems, we are interested in sources with underlying discrete nature. Our method can be viewed as a multi-source extension to the recently proposed score distillation sampling scheme.
  arXiv  Detail & Related papers  (2023-06-26T04:12:40Z)
• Boosting Fast and High-Quality Speech Synthesis with Linear Diffusion [85.54515118077825]
  This paper proposes a linear diffusion model (LinDiff) based on an ordinary differential equation to simultaneously reach fast inference and high sample quality. To reduce computational complexity, LinDiff employs a patch-based processing approach that partitions the input signal into small patches. Our model can synthesize speech of a quality comparable to that of autoregressive models with faster synthesis speed.
  arXiv  Detail & Related papers  (2023-06-09T07:02:43Z)
• Separate And Diffuse: Using a Pretrained Diffusion Model for Improving Source Separation [99.19786288094596]
  We show how the upper bound can be generalized to the case of random generative models. We show state-of-the-art results on 2, 3, 5, 10, and 20 speakers on multiple benchmarks.
  arXiv  Detail & Related papers  (2023-01-25T18:21:51Z)
• Unsupervised Audio Source Separation Using Differentiable Parametric Source Models [8.80867379881193]
  We propose an unsupervised model-based deep learning approach to musical source separation. A neural network is trained to reconstruct the observed mixture as a sum of the sources. The experimental evaluation on a vocal ensemble separation task shows that the proposed method outperforms learning-free methods.
  arXiv  Detail & Related papers  (2022-01-24T11:05:30Z)
• Deblurring via Stochastic Refinement [85.42730934561101]
  We present an alternative framework for blind deblurring based on conditional diffusion models. Our method is competitive in terms of distortion metrics such as PSNR.
  arXiv  Detail & Related papers  (2021-12-05T04:36:09Z)
• Learning the Truth From Only One Side of the Story [58.65439277460011]
  We focus on generalized linear models and show that without adjusting for this sampling bias, the model may converge suboptimally or even fail to converge to the optimal solution. We propose an adaptive approach that comes with theoretical guarantees and show that it outperforms several existing methods empirically.
  arXiv  Detail & Related papers  (2020-06-08T18:20:28Z)

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.