BUDDy: Single-Channel Blind Unsupervised Dereverberation with Diffusion Models

• URL: http://arxiv.org/abs/2405.04272v1
• Date: Tue, 7 May 2024 12:41:31 GMT
• Title: BUDDy: Single-Channel Blind Unsupervised Dereverberation with Diffusion Models
• Authors: Eloi Moliner, Jean-Marie Lemercier, Simon Welker, Timo Gerkmann, Vesa Välimäki,
• Abstract summary: We present an unsupervised single-channel method for joint blind dereverberation and room impulse response estimation. We parameterize the reverberation operator using a filter with exponential decay for each frequency subband, and iteratively estimate the corresponding parameters as the speech utterance gets refined.
• Score: 21.66936362048033
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we present an unsupervised single-channel method for joint blind dereverberation and room impulse response estimation, based on posterior sampling with diffusion models. We parameterize the reverberation operator using a filter with exponential decay for each frequency subband, and iteratively estimate the corresponding parameters as the speech utterance gets refined along the reverse diffusion trajectory. A measurement consistency criterion enforces the fidelity of the generated speech with the reverberant measurement, while an unconditional diffusion model implements a strong prior for clean speech generation. Without any knowledge of the room impulse response nor any coupled reverberant-anechoic data, we can successfully perform dereverberation in various acoustic scenarios. Our method significantly outperforms previous blind unsupervised baselines, and we demonstrate its increased robustness to unseen acoustic conditions in comparison to blind supervised methods. Audio samples and code are available online.

Related papers

• Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers [49.97755400231656]
  We present the first performance guarantee with explicit dimensional general score-mismatched diffusion samplers. We show that score mismatches result in an distributional bias between the target and sampling distributions, proportional to the accumulated mismatch between the target and training distributions. This result can be directly applied to zero-shot conditional samplers for any conditional model, irrespective of measurement noise.
  arXiv  Detail & Related papers  (2024-10-17T16:42:12Z)
• Diffusion-based Unsupervised Audio-visual Speech Enhancement [26.937216751657697]
  This paper proposes a new unsupervised audiovisual speech enhancement (AVSE) approach. It combines a diffusion-based audio-visual speech generative model with a non-negative matrix factorization (NMF) noise model. Experimental results confirm that the proposed AVSE approach not only outperforms its audio-only counterpart but also generalizes better than a recent supervisedgenerative AVSE method.
  arXiv  Detail & Related papers  (2024-10-04T12:22:54Z)
• Unsupervised Blind Joint Dereverberation and Room Acoustics Estimation with Diffusion Models [21.669363620480333]
  We present an unsupervised method for blind dereverberation and room impulse response estimation, called BUDDy. In a blind scenario where the room impulse response is unknown, BUDDy successfully performs speech dereverberation. Unlike supervised methods, which often struggle to generalize, BUDDy seamlessly adapts to different acoustic conditions.
  arXiv  Detail & Related papers  (2024-08-14T11:31:32Z)
• High-Fidelity Speech Synthesis with Minimal Supervision: All Using Diffusion Models [56.00939852727501]
  Minimally-supervised speech synthesis decouples TTS by combining two types of discrete speech representations. Non-autoregressive framework enhances controllability, and duration diffusion model enables diversified prosodic expression.
  arXiv  Detail & Related papers  (2023-09-27T09:27:03Z)
• 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)
• Diffusion Posterior Sampling for Informed Single-Channel Dereverberation [15.16865739526702]
  We present an informed single-channel dereverberation method based on conditional generation with diffusion models. With knowledge of the room impulse response, the anechoic utterance is generated via reverse diffusion. The proposed approach is largely more robust to measurement noise compared to a state-of-the-art informed single-channel dereverberation method.
  arXiv  Detail & Related papers  (2023-06-21T14:14:05Z)
• Blind Audio Bandwidth Extension: A Diffusion-Based Zero-Shot Approach [4.030910640265943]
  In cases where the lowpass degradation is unknown, such as in restoring historical audio recordings, this becomes a blind problem. This paper introduces a novel method called BABE that addresses the blind problem in a zero-shot setting. BABE exhibits robust generalization capabilities when enhancing real historical recordings.
  arXiv  Detail & Related papers  (2023-06-02T10:47:15Z)
• Reflected Diffusion Models [93.26107023470979]
  We present Reflected Diffusion Models, which reverse a reflected differential equation evolving on the support of the data. Our approach learns the score function through a generalized score matching loss and extends key components of standard diffusion models.
  arXiv  Detail & Related papers  (2023-04-10T17:54:38Z)
• DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection [89.49600182243306]
  We reformulate the reconstruction process using a diffusion model into a noise-to-norm paradigm. We propose a rapid one-step denoising paradigm, significantly faster than the traditional iterative denoising in diffusion models. The segmentation sub-network predicts pixel-level anomaly scores using the input image and its anomaly-free restoration.
  arXiv  Detail & Related papers  (2023-03-15T16:14:06Z)
• A Study on Speech Enhancement Based on Diffusion Probabilistic Model [63.38586161802788]
  We propose a diffusion probabilistic model-based speech enhancement model (DiffuSE) model that aims to recover clean speech signals from noisy signals. The experimental results show that DiffuSE yields performance that is comparable to related audio generative models on the standardized Voice Bank corpus task.
  arXiv  Detail & Related papers  (2021-07-25T19:23:18Z)

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.