# URGENT Challenge: Universality, Robustness, and Generalizability For Speech Enhancement

arXiv: https://arxiv.org/abs/2406.04660 · HTML: https://mlsanity.com/paper/2406.04660/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jun 2024.

## Built on by (most cited first, 17 of 17)

- [AnyEnhance: A Unified Generative Model with Prompt-Guidance and Self-Critic for Voice Enhancement](https://mlsanity.com/paper/2501.15417/) (2025)
- [Universal Speech Enhancement with Regression and Generative Mamba](https://mlsanity.com/paper/2505.21198/) (2025)
- [Multi-Metric Preference Alignment for Generative Speech Restoration](https://mlsanity.com/paper/2508.17229/) (2025)
- [EDNet: A Versatile Speech Enhancement Framework with Gating Mamba Mechanism and Phase Shift-Invariant Training](https://mlsanity.com/paper/2506.16231/) (2025)
- [MB-RIRs: a Synthetic Room Impulse Response Dataset with Frequency-Dependent Absorption Coefficients](https://mlsanity.com/paper/2507.09750/) (2025)
- [Training-Free Multi-Step Audio Source Separation](https://mlsanity.com/paper/2505.19534/) (2025)
- [DeepFilterGAN: A Full-band Real-time Speech Enhancement System with GAN-based Stochastic Regeneration](https://mlsanity.com/paper/2505.23515/) (2025)
- [Audio Generation Through Score-Based Generative Modeling: Design Principles and Implementation](https://mlsanity.com/paper/2506.08457/) (2025)
- [GAP-URGENet: A Generative-Predictive Fusion Framework for Universal Speech Enhancement](https://mlsanity.com/paper/2604.01832/) (2026)
- [Model as Loss: A Self-Consistent Training Paradigm](https://mlsanity.com/paper/2505.21156/) (2025)
- [Unsupervised Speech Enhancement using Data-defined Priors](https://mlsanity.com/paper/2509.22942/) (2025)
- [Contract-Driven QoE Auditing for Speech and Singing Services: From MOS Regression to Service Graphs](https://mlsanity.com/paper/2512.04827/) (2025)
- [StuPASE: Towards Low-Hallucination Studio-Quality Generative Speech Enhancement](https://mlsanity.com/paper/2603.09234/) (2026)
- [Efficient Multi-View 3D Object Detection by Dynamic Token Selection and Fine-Tuning](https://mlsanity.com/paper/2604.13586/) (2026)
- [UniPASE: A Generative Model for Universal Speech Enhancement with High Fidelity and Low Hallucinations](https://mlsanity.com/paper/2604.14606/) (2026)
- [TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation](https://mlsanity.com/paper/2606.29575/) (2026)
- [Acoustic domain shift in spoken language identification from systematic domain generalization evaluation to real-world application](https://mlsanity.com/paper/2609.31759/) (2026)

## Abstract (arXiv)

The last decade has witnessed significant advancements in deep learning-based speech enhancement (SE). However, most existing SE research has limitations on the coverage of SE sub-tasks, data diversity and amount, and evaluation metrics. To fill this gap and promote research toward universal SE, we establish a new SE challenge, named URGENT, to focus on the universality, robustness, and generalizability of SE. We aim to extend the SE definition to cover different sub-tasks to explore the limits of SE models, starting from denoising, dereverberation, bandwidth extension, and declipping. A novel framework is proposed to unify all these sub-tasks in a single model, allowing the use of all existing SE approaches. We collected public speech and noise data from different domains to construct diverse evaluation data. Finally, we discuss the insights gained from our preliminary baseline experiments based on both generative and discriminative SE methods with 12 curated metrics.