U-DREAM: Unsupervised Dereverberation guided by a Reverberation Model

• URL: http://arxiv.org/abs/2507.14237v1
• Date: Thu, 17 Jul 2025 12:26:18 GMT
• Title: U-DREAM: Unsupervised Dereverberation guided by a Reverberation Model
• Authors: Louis Bahrman, Mathieu Fontaine, Gaël Richard,
• Abstract summary: This paper explores the outcome of training state-ofthe-art dereverberation models with supervision settings ranging from weakly-supervised to fully unsupervised.<n>Most of the existing deep learning approaches typically require paired dry and reverberant data, which are difficult to obtain in practice.<n>We develop instead a sequential learning strategy motivated by a bayesian formulation of the dereverberation problem, wherein acoustic parameters and dry signals are estimated from reverberant inputs using deep neural networks.
• Score: 12.192022160630165
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper explores the outcome of training state-ofthe-art dereverberation models with supervision settings ranging from weakly-supervised to fully unsupervised, relying solely on reverberant signals and an acoustic model for training. Most of the existing deep learning approaches typically require paired dry and reverberant data, which are difficult to obtain in practice. We develop instead a sequential learning strategy motivated by a bayesian formulation of the dereverberation problem, wherein acoustic parameters and dry signals are estimated from reverberant inputs using deep neural networks, guided by a reverberation matching loss. Our most data-efficient variant requires only 100 reverberation-parameter-labelled samples to outperform an unsupervised baseline, demonstrating the effectiveness and practicality of the proposed method in low-resource scenarios.

Related papers

• A Hybrid Model for Weakly-Supervised Speech Dereverberation [2.731944614640173]
  This paper introduces a new training strategy to improve speech dereverberation systems using minimal acoustic information and reverberant (wet) speech.<n> Experimental results demonstrate that our method achieves more consistent performance across various objective metrics used in speech dereverberation than the state-of-the-art.
  arXiv  Detail & Related papers  (2025-02-06T09:21:22Z)
• Unsupervised Blind Joint Dereverberation and Room Acoustics Estimation with Diffusion Models [21.669363620480333]
  This paper presents an unsupervised method for single-channel blind dereverberation and room impulse response (RIR) estimation, called BUDDy.<n>We design a parametric filter representing the RIR, with exponential decay for each frequency subband.<n>We study BUDDy's performance for RIR estimation and observe it surpasses a state-of-the-art supervised-based estimator on mismatched acoustic conditions.
  arXiv  Detail & Related papers  (2024-08-14T11:31:32Z)
• Impact of Noisy Supervision in Foundation Model Learning [91.56591923244943]
  This paper is the first work to comprehensively understand and analyze the nature of noise in pre-training datasets.<n>We propose a tuning method (NMTune) to affine the feature space to mitigate the malignant effect of noise and improve generalization.
  arXiv  Detail & Related papers  (2024-03-11T16:22:41Z)
• Unmasking Bias in Diffusion Model Training [40.90066994983719]
  Denoising diffusion models have emerged as a dominant approach for image generation. They still suffer from slow convergence in training and color shift issues in sampling. In this paper, we identify that these obstacles can be largely attributed to bias and suboptimality inherent in the default training paradigm.
  arXiv  Detail & Related papers  (2023-10-12T16:04:41Z)
• Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks [91.15120211190519]
  This paper aims to understand the nature of noise in pre-training datasets and to mitigate its impact on downstream tasks. We propose a light-weight black-box tuning method (NMTune) to affine the feature space to mitigate the malignant effect of noise.
  arXiv  Detail & Related papers  (2023-09-29T06:18:15Z)
• Universal Adversarial Defense in Remote Sensing Based on Pre-trained Denoising Diffusion Models [17.283914361697818]
  Deep neural networks (DNNs) have risen to prominence as key solutions in numerous AI applications for earth observation (AI4EO) This paper presents a novel Universal Adversarial Defense approach in Remote Sensing Imagery (UAD-RS)
  arXiv  Detail & Related papers  (2023-07-31T17:21:23Z)
• Advancing underwater acoustic target recognition via adaptive data pruning and smoothness-inducing regularization [27.039672355700198]
  We propose a strategy based on cross-entropy to prune excessively similar segments in training data. We generate noisy samples and apply smoothness-inducing regularization based on KL divergence to mitigate overfitting.
  arXiv  Detail & Related papers  (2023-04-24T08:30:41Z)
• DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection [80.20339155618612]
  DiffusionAD is a novel anomaly detection pipeline comprising a reconstruction sub-network and a segmentation sub-network.<n>A rapid one-step denoising paradigm achieves hundreds of times acceleration while preserving comparable reconstruction quality.<n>Considering the diversity in the manifestation of anomalies, we propose a norm-guided paradigm to integrate the benefits of multiple noise scales.
  arXiv  Detail & Related papers  (2023-03-15T16:14:06Z)
• Latent Class-Conditional Noise Model [54.56899309997246]
  We introduce a Latent Class-Conditional Noise model (LCCN) to parameterize the noise transition under a Bayesian framework. We then deduce a dynamic label regression method for LCCN, whose Gibbs sampler allows us efficiently infer the latent true labels. Our approach safeguards the stable update of the noise transition, which avoids previous arbitrarily tuning from a mini-batch of samples.
  arXiv  Detail & Related papers  (2023-02-19T15:24:37Z)
• Unsupervised vocal dereverberation with diffusion-based generative models [12.713895991763867]
  We propose an unsupervised method to remove a general kind of artificial reverb for music without requiring pairs of data for training. We show through objective and perceptual evaluations that our method outperforms the current leading vocal dereverberation benchmarks.
  arXiv  Detail & Related papers  (2022-11-08T09:43:01Z)
• Robust Training under Label Noise by Over-parameterization [41.03008228953627]
  We propose a principled approach for robust training of over-parameterized deep networks in classification tasks where a proportion of training labels are corrupted. The main idea is yet very simple: label noise is sparse and incoherent with the network learned from clean data, so we model the noise and learn to separate it from the data. Remarkably, when trained using such a simple method in practice, we demonstrate state-of-the-art test accuracy against label noise on a variety of real datasets.
  arXiv  Detail & Related papers  (2022-02-28T18:50:10Z)
• Jo-SRC: A Contrastive Approach for Combating Noisy Labels [58.867237220886885]
  We propose a noise-robust approach named Jo-SRC (Joint Sample Selection and Model Regularization based on Consistency) Specifically, we train the network in a contrastive learning manner. Predictions from two different views of each sample are used to estimate its "likelihood" of being clean or out-of-distribution.
  arXiv  Detail & Related papers  (2021-03-24T07:26:07Z)
• Automatic Recall Machines: Internal Replay, Continual Learning and the Brain [104.38824285741248]
  Replay in neural networks involves training on sequential data with memorized samples, which counteracts forgetting of previous behavior caused by non-stationarity. We present a method where these auxiliary samples are generated on the fly, given only the model that is being trained for the assessed objective. Instead the implicit memory of learned samples within the assessed model itself is exploited.
  arXiv  Detail & Related papers  (2020-06-22T15:07:06Z)

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.