DGMO: Training-Free Audio Source Separation through Diffusion-Guided Mask Optimization

• URL: http://arxiv.org/abs/2506.02858v2
• Date: Thu, 05 Jun 2025 04:46:57 GMT
• Title: DGMO: Training-Free Audio Source Separation through Diffusion-Guided Mask Optimization
• Authors: Geonyoung Lee, Geonhee Han, Paul Hongsuck Seo,
• Abstract summary: Language-queried Audio Source Separation (LASS) enables open-vocabulary sound separation via natural language queries.<n>We introduce a training-free framework leveraging generative priors for zero-shot LASS.<n>Our approach effectively repurposes pretrained diffusion models for source separation, achieving competitive performance without task-specific supervision.
• Score: 6.6567375919025995
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Language-queried Audio Source Separation (LASS) enables open-vocabulary sound separation via natural language queries. While existing methods rely on task-specific training, we explore whether pretrained diffusion models, originally designed for audio generation, can inherently perform separation without further training. In this study, we introduce a training-free framework leveraging generative priors for zero-shot LASS. Analyzing naive adaptations, we identify key limitations arising from modality-specific challenges. To address these issues, we propose Diffusion-Guided Mask Optimization (DGMO), a test-time optimization framework that refines spectrogram masks for precise, input-aligned separation. Our approach effectively repurposes pretrained diffusion models for source separation, achieving competitive performance without task-specific supervision. This work expands the application of diffusion models beyond generation, establishing a new paradigm for zero-shot audio separation. The code is available at: https://wltschmrz.github.io/DGMO/

Related papers

• ZeroSep: Separate Anything in Audio with Zero Training [42.19808124670159]
  Audio source separation is fundamental for machines to understand complex acoustic environments.<n>Current supervised deep learning approaches, while powerful, are limited by the need for extensive, task-specific labeled data.<n>We investigate whether pre-trained text-guided audio diffusion models can overcome these limitations.<n>We make a surprising discovery: zero-shot source separation can be achieved purely through a pre-trained text-guided audio diffusion model.
  arXiv  Detail & Related papers  (2025-05-29T16:31:45Z)
• Generalized Interpolating Discrete Diffusion [65.74168524007484]
  Masked diffusion is a popular choice due to its simplicity and effectiveness.<n>We derive the theoretical backbone of a family of general interpolating discrete diffusion processes.<n>Exploiting GIDD's flexibility, we explore a hybrid approach combining masking and uniform noise.
  arXiv  Detail & Related papers  (2025-03-06T14:30:55Z)
• 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)
• Diffusion-based Unsupervised Audio-visual Speech Enhancement [26.937216751657697]
  This paper proposes a new unsupervised audio-visual speech enhancement (AVSE) approach.<n>It combines a diffusion-based audio-visual speech generative model with a non-negative matrix factorization (NMF) noise model.<n> Experimental results confirm that the proposed AVSE approach not only outperforms its audio-only counterpart but also generalizes better than a recent supervised-generative AVSE method.
  arXiv  Detail & Related papers  (2024-10-04T12:22:54Z)
• OpenSep: Leveraging Large Language Models with Textual Inversion for Open World Audio Separation [9.453883041423468]
  We propose OpenSep, a novel framework that leverages large language models (LLMs) for automated audio separation. OpenSep uses textual inversion to generate captions from audio mixtures with off-the-shelf audio captioning models, effectively parsing the sound sources present. It then employs few-shot LLM prompting to extract detailed audio properties of each parsed source, facilitating separation in unseen mixtures.
  arXiv  Detail & Related papers  (2024-09-28T06:59:52Z)
• DDTSE: Discriminative Diffusion Model for Target Speech Extraction [62.422291953387955]
  We introduce the Discriminative Diffusion model for Target Speech Extraction (DDTSE) We apply the same forward process as diffusion models and utilize the reconstruction loss similar to discriminative methods. We devise a two-stage training strategy to emulate the inference process during model training.
  arXiv  Detail & Related papers  (2023-09-25T04:58:38Z)
• Unsupervised speech enhancement with diffusion-based generative models [0.0]
  We introduce an alternative approach that operates in an unsupervised manner, leveraging the generative power of diffusion models. We develop a posterior sampling methodology for speech enhancement by combining the learnt clean speech prior with a noise model for speech signal inference. We show promising results compared to a recent variational auto-encoder (VAE)-based unsupervised approach and a state-of-the-art diffusion-based supervised method.
  arXiv  Detail & Related papers  (2023-09-19T09:11:31Z)
• DiffSED: Sound Event Detection with Denoising Diffusion [70.18051526555512]
  We reformulate the SED problem by taking a generative learning perspective. Specifically, we aim to generate sound temporal boundaries from noisy proposals in a denoising diffusion process. During training, our model learns to reverse the noising process by converting noisy latent queries to the groundtruth versions.
  arXiv  Detail & Related papers  (2023-08-14T17:29:41Z)
• An Efficient Membership Inference Attack for the Diffusion Model by Proximal Initialization [58.88327181933151]
  In this paper, we propose an efficient query-based membership inference attack (MIA) Experimental results indicate that the proposed method can achieve competitive performance with only two queries on both discrete-time and continuous-time diffusion models. To the best of our knowledge, this work is the first to study the robustness of diffusion models to MIA in the text-to-speech task.
  arXiv  Detail & Related papers  (2023-05-26T16:38:48Z)
• Dior-CVAE: Pre-trained Language Models and Diffusion Priors for Variational Dialog Generation [70.2283756542824]
  Dior-CVAE is a hierarchical conditional variational autoencoder (CVAE) with diffusion priors to address these challenges. We employ a diffusion model to increase the complexity of the prior distribution and its compatibility with the distributions produced by a PLM. Experiments across two commonly used open-domain dialog datasets show that our method can generate more diverse responses without large-scale dialog pre-training.
  arXiv  Detail & Related papers  (2023-05-24T11:06:52Z)
• A Cheaper and Better Diffusion Language Model with Soft-Masked Noise [62.719656543880596]
  Masked-Diffuse LM is a novel diffusion model for language modeling, inspired by linguistic features in languages. Specifically, we design a linguistic-informed forward process which adds corruptions to the text through strategically soft-masking to better noise the textual data. We demonstrate that our Masked-Diffuse LM can achieve better generation quality than the state-of-the-art diffusion models with better efficiency.
  arXiv  Detail & Related papers  (2023-04-10T17:58:42Z)
• DiffusionRet: Generative Text-Video Retrieval with Diffusion Model [56.03464169048182]
  Existing text-video retrieval solutions focus on maximizing the conditional likelihood, i.e., p(candidates|query) We creatively tackle this task from a generative viewpoint and model the correlation between the text and the video as their joint probability p(candidates,query) This is accomplished through a diffusion-based text-video retrieval framework (DiffusionRet), which models the retrieval task as a process of gradually generating joint distribution from noise.
  arXiv  Detail & Related papers  (2023-03-17T10:07:19Z)

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.