# U-DREAM: Unsupervised Dereverberation guided by a Reverberation Model

arXiv: https://arxiv.org/abs/2507.14237 · HTML: https://mlsanity.com/paper/2507.14237/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 55 references that are in the map.
- First posted on arXiv 17 Jul 2025.

## Builds on (most cited first, 23 of 23)

- [GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks](https://mlsanity.com/paper/1711.02257/) (2017)
- [SDR - half-baked or well done?](https://mlsanity.com/paper/1811.02508/) (2018)
- [Speech Enhancement and Dereverberation with Diffusion-based Generative Models](https://mlsanity.com/paper/2208.05830/) (2022)
- [Pyroomacoustics: A Python package for audio room simulations and array processing algorithms](https://mlsanity.com/paper/1710.04196/) (2017)
- [FullSubNet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement](https://mlsanity.com/paper/2010.15508/) (2020)
- [EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation](https://mlsanity.com/paper/2406.06185/) (2024)
- [GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse Problems with Denoising Diffusion Restoration](https://mlsanity.com/paper/2301.12686/) (2023)
- [MetricGAN-U: Unsupervised speech enhancement/ dereverberation based only on noisy/ reverberated speech](https://mlsanity.com/paper/2110.05866/) (2021)
- [TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement](https://mlsanity.com/paper/2408.03440/) (2024)
- [Unsupervised Blind Joint Dereverberation and Room Acoustics Estimation with Diffusion Models](https://mlsanity.com/paper/2408.07472/) (2024)
- [Speech Dereverberation with A Reverberation Time Shortening Target](https://mlsanity.com/paper/2204.08765/) (2022)
- [Diffusion Posterior Sampling for Informed Single-Channel Dereverberation](https://mlsanity.com/paper/2306.12286/) (2023)
- [Convolutive Prediction for Monaural Speech Dereverberation and Noisy-Reverberant Speaker Separation](https://mlsanity.com/paper/2108.07376/) (2021)
- [Receptive Field Analysis of Temporal Convolutional Networks for Monaural Speech Dereverberation](https://mlsanity.com/paper/2204.06439/) (2022)
- [USDnet: Unsupervised Speech Dereverberation via Neural Forward Filtering](https://mlsanity.com/paper/2402.00820/) (2024)
- [RVAE-EM: Generative speech dereverberation based on recurrent variational auto-encoder and convolutive transfer function](https://mlsanity.com/paper/2309.08157/) (2023)
- [TeCANet: Temporal-Contextual Attention Network for Environment-Aware Speech Dereverberation](https://mlsanity.com/paper/2103.16849/) (2021)
- [CycleGAN-Based Unpaired Speech Dereverberation](https://mlsanity.com/paper/2203.15652/) (2022)
- [DIFFRENT: A Diffusion Model for Recording Environment Transfer of Speech](https://mlsanity.com/paper/2401.08102/) (2024)
- [Speech dereverberation constrained on room impulse response characteristics](https://mlsanity.com/paper/2407.08657/) (2024)
- [AnCoGen: Analysis, Control and Generation of Speech with a Masked Autoencoder](https://mlsanity.com/paper/2501.05332/) (2025)
- [A Composite T60 Regression and Classification Approach for Speech Dereverberation](https://mlsanity.com/paper/2302.04932/) (2023)
- [A Hybrid Model for Weakly-Supervised Speech Dereverberation](https://mlsanity.com/paper/2502.06839/) (2025)

## Abstract (arXiv)

This paper explores the outcome of training state-of-the-art dereverberation models with supervision settings ranging from weakly-supervised to virtually 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 maximum-likelihood 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-labeled samples to outperform an unsupervised baseline, demonstrating the effectiveness and practicality of the proposed method in low-resource scenarios.