---
title: URGENT Speech Enhancement Challenge
url: https://www.emergentmind.com/topics/urgent-speech-enhancement-challenge
type: topic
---

# URGENT Speech Enhancement Challenge

The URGENT Speech Enhancement Challenge denotes a sequence of benchmark efforts that study speech enhancement under increasingly heterogeneous conditions. In the literature, the label first appears in a 2019 audio-visual challenge built around a real noisy binaural corpus and subjective evaluation, and from 2024 onward it designates a broader universal speech enhancement series centered on multiple distortion types, multiple sampling frequencies, multilinguality, curated public training resources, and mixed objective–subjective evaluation [1910.00424][2406.04660][2505.23212][2601.13531]. Across these stages, the challenge has served less as a single fixed task than as an evolving benchmark program for comparing discriminative, generative, and hybrid enhancement systems under common conditions.

## 1. Historical development and challenge scope

The challenge literature describes a clear progression from realistic audio-visual enhancement toward universal speech enhancement. The 2019 paper presents a “first of its kind” audio-visual speech enhancement challenge in real-noisy settings, while the 2024, 2025, and 2026 papers expand URGENT into a benchmark series for universal, robust, and generalizable enhancement across distortions, sampling rates, languages, and speech styles [1910.00424][2406.04660][2505.23212][2601.13531].

| Edition | Core scope | Distinctive features |
|---|---|---|
| 2019 AV challenge [1910.00424] | Audio-visual speech enhancement | Real noisy ASPIRE corpus; binaural speech; subjective MUSHRA baseline |
| URGENT 2024 [2406.04660] | Universal SE | Denoising, dereverberation, bandwidth extension, declipping; multiple sampling frequencies; 12 curated metrics |
| Interspeech 2025 [2505.23212] | Second URGENT edition | Seven distortion types; multilingual training and evaluation; two training-scale tracks |
| ICASSP 2026 [2601.13531] | Two-track URGENT | Track 1 universal SE; Track 2 MOS prediction for enhanced speech |

From 2024 onward, the core task is formulated as
\[
\hat{\mathbf{x}} = \operatorname{SE}(\mathcal{F}(\mathbf{x})) ,
\]
where \(\mathbf{x}\) is the desired speech, \(\mathcal{F}(\cdot)\) is a distortion process, and \(\hat{\mathbf{x}}\) is the enhanced output [2406.04660][2505.23212]. In the 2024 overview this broader task initially covers denoising, dereverberation, bandwidth extension, and declipping, with inputs at \(8\), \(16\), \(22.05\), \(24\), \(32\), \(44.1\), and \(48\) kHz [2406.04660]. The 2025 edition raises the distortion count to seven by adding codec loss, packet loss, and wind noise, and explicitly studies language dependency and data scalability [2505.23212]. The 2026 edition further broadens speech diversity to include different ages, accents, whispered speech, singing voice, and emotional expression, and adds a second track for speech quality assessment [2601.13531].

## 2. Audio-visual precursor: the 2019 real-noisy benchmark

The 2019 URGENT audio-visual challenge is organized around **ASPIRE**, a “high-quality AV binaural speech corpus recorded in real noisy settings” [1910.00424]. The noisy recordings were made in the University of Stirling cafeteria and restaurant during busy lunch times, from **11:30 to 1:30**, and matched booth recordings were also collected. ASPIRE contains **5 speakers total**, **2 male, 3 female**, with age range **23 to 55**, mixed English accents, and **10,000 utterances** overall: **5,000 in real noisy settings** and **5,000 in an acoustically isolated booth** [1910.00424].

The sentence design follows the AV Grid template. Each utterance is a six-word command sentence with the structure command–colour–preposition–letter–digit–adverb, and each speaker produced **1000 utterances per talker** in real noisy settings and **1000 utterances per talker** in the booth [1910.00424]. Video was recorded with an **Apple iPad-mini2** at **30 frames per second** and **1080p**, positioned at **90 cm** from the speaker, and high-quality binaural audio was recorded with a **Zoom H4n Pro recorder** at **44.1 kHz** using a binaural microphone worn by a listener at approximately **140 cm** [1910.00424].

The benchmark is notable because the speech is recorded directly in real environments rather than created by additive mixing. The paper emphasizes nonstationary and multi-source background noise, real reverberation, head movement, face obscuration, and the possibility of the **Lombard effect** [1910.00424]. Postprocessing used clap-based audio/video synchronization, **Gentle**, a forced aligner built on **Kaldi**, manual boundary checking, and video pixelation for privacy [1910.00424].

The benchmark task is audio-visual speech enhancement on real noisy binaural speech, with training on **Grid speech mixed with ChiME3 noises** and testing on ASPIRE. The baseline systems were **SEAGN**, **Spectrum Subtraction (SS)**, **Log-minimum mean square error (LMMSE)**, **audio-only CochleaNet**, and **AV CochleaNet** [1910.00424]. Training pooled SNRs from **−12 dB to 9 dB** in **3 dB** steps, with **21000 utterances** combined for SNR-independent training [1910.00424]. Evaluation used a MUSHRA-style listening test with **20 native English speakers**, **20 randomly selected utterances**, and a **0–100** quality scale [1910.00424]. The principal finding was that **AV CochleaNet performed best** and outperformed the audio-only CochleaNet baseline, supporting the challenge premise that visual information improves enhancement under reverberant, multi-source, real-noisy conditions [1910.00424].

## 3. URGENT 2024: universal speech enhancement as a benchmark program

The 2024 URGENT challenge redefines speech enhancement as a broader universal problem rather than a denoising-only task. The overview paper explicitly states that the challenge aims to cover different sub-tasks, data diversity and amount, and evaluation metrics, and it broadens the task definition to **denoising**, **dereverberation**, **bandwidth extension**, and **declipping** [2406.04660]. It is restricted to **single-channel** signals in its first edition, while allowing variable sampling frequencies and multiple distortion types within one system [2406.04660].

A central design feature is sample-rate handling. The paper proposes either **sampling-frequency-independent (SFI) STFT-based design** for models such as **BSRNN** and **TF-GridNet**, or an upsample-to-48-kHz strategy for fixed-rate models such as **Conv-TasNet** [2406.04660]. In the preliminary challenge experiments, the curated pool contains roughly **~1300 hours of speech** and **~250 hours of noise**, and the fixed simulated benchmark used **~400 hours** for training, **~30 hours** for validation, and **~15 hours** for test, with SNR range **-5 dB to 20 dB** and reverberation added with probability **0.5** [2406.04660].

Evaluation in the initial overview is deliberately broad. The paper reports **12 curated metrics** spanning intrusive, non-intrusive, downstream-task-independent, and downstream-task-dependent categories, including **POLQA**, **PESQ**, **ESTOI**, **SDR**, **MCD**, **LSD**, **DNSMOS**, **NISQA**, **PhnSim**, **SpeechBERTScore**, **SpkSim**, and **WAcc** [2406.04660]. The preliminary baselines are **OM-LSA**, **VoiceFixer**, **Conv-TasNet**, **BSRNN**, and **TF-GridNet**, and the reported trend is that the mapping-based discriminative models, especially **BSRNN** and **TF-GridNet**, are much stronger universal baselines than masking-based **Conv-TasNet**, particularly on bandwidth-related restoration [2406.04660]. The same experiments also show the classic generative tradeoff: **VoiceFixer** is strong on **DNSMOS** and **NISQA** but weak on intrusive and content-preservation measures, exposing hallucination behavior under the broader metric suite [2406.04660].

The post-challenge analysis in “Lessons Learned from the URGENT 2024 Speech Enhancement Challenge” extends these observations from benchmark design to benchmark pathology [2506.01611]. It reports **three phases**—validation, non-blind test, and blind test—with **1000 samples** in each phase, and a blind test containing **500 simulated samples** and **500 real recordings**, with **21 participating teams** in the final blind test [2506.01611]. The analysis identifies two systematic data problems. First, declared sampling frequency often mismatched effective bandwidth: **~25% of LibriTTS** showed mismatch, while **~100% of DNS5 LibriVox** speech and **~100% of CommonVoice 11.0 English** showed this issue [2506.01611]. Second, training labels in nominally clean corpora were often noisy: the paper found approximately **2000 speech labels with negative WADA-SNRs** [2506.01611]. It also finds that the hardest conditions were **speech overlap**, **strong wideband background noise** or **instantaneous noise**, and **high reverberation**, and that nominal SNR is not a reliable proxy for SE difficulty [2506.01611]. In the same analysis, the overall combined ranking achieved **KRCC between MOS rank and the overall challenge rank = 0.73**, while **UTMOS** and **SCOREQ** showed the highest correlations with MOS [2506.01611].

## 4. Interspeech 2025: multilinguality, seven distortions, and multi-metric ranking

The Interspeech 2025 URGENT Speech Enhancement Challenge is the second edition of the universal SE series [2505.23212]. It is explicitly framed around four underexplored issues: **language dependency**, **universality across more distortion types**, **data scalability**, and **how to exploit noisy training data** [2505.23212]. Compared with URGENT 2024, it expands the distortion set from four to **seven**: additive noise, reverberation, clipping, bandwidth limitation, codec loss, packet loss, and wind noise, with each sample degraded by **up to five distortions simultaneously** [2505.23212]. The challenge uses two training tracks: about **2.5k hours of speech** in Track 1 and about **60k hours of speech** in Track 2 [2505.23212].

Multilinguality becomes a first-class component of validity. Training covers **five languages**—English, German, French, Spanish, and Chinese—and the **blind test set** adds **Japanese** as an unseen language, with **150 samples per language** and **900 total samples**, half simulated and half real [2505.23212]. The challenge uses **14 metrics** grouped into five categories: non-intrusive SE metrics (**DNSMOS**, **NISQA**, **UTMOS**), intrusive SE metrics (**POLQA**, **PESQ**, **ESTOI**, **SDR**, **MCD**, **LSD**), downstream-task-independent metrics (**LPS**, **SBS**), downstream-task-dependent metrics (**SpkSim**, **CAcc**), and subjective **MOS** via **ITU-T P.808** [2505.23212]. The final ranking is not based on a single metric but on a three-step procedure inspired by the **Friedman test**: rank each metric, average ranks within each category, then average category-wise rankings, with a lower final score indicating a better system [2505.23212].

The 2025 challenge received **32 submissions total**. The printed subset of the Track 1 leaderboard shows **T1** as the best overall system with final ranking score **2.97**, and it is explicitly characterized as **purely discriminative**; most of the remaining competitive systems are **hybrid** [2505.23212]. The most revealing entry is the purely generative **T13**. It ranked first on **DNSMOS**, **NISQA**, **UTMOS**, and **MOS**, with **MOS 3.69**, yet performed very poorly on intrusive and content-sensitive measures, including **POLQA 1.99**, **PESQ 1.34**, **ESTOI 0.54**, **SDR -12.28**, **SpkSim 0.47**, and **CAcc 67.87%** [2505.23212]. The same paper reports strong language dependence for this generative system: **Chinese CAcc 20.1** and **Japanese CAcc 36.8**, despite high DNSMOS, whereas the top discriminative model **T1** remains relatively stable across languages [2505.23212]. These results establish one of the defining challenge debates: subjective naturalness and non-intrusive quality can diverge sharply from content preservation and speaker fidelity.

## 5. System families and architectural patterns shaped by URGENT

A distinct research ecosystem has formed around URGENT-style benchmarks, and several recurring design patterns are visible in challenge papers. One line favors **regression-first universal models**. **USEMamba**, a state-space model with sampling-frequency-independent feature extraction and a distortion-aware combination of regression and generation, achieved **2nd place in Track 1 during the blind test phase** of URGENT 2025 despite being trained on only a subset of the data [2505.21198]. Its central claim is that regression works well for most distortions, while a generative variant is more suitable for **packet loss** and **bandwidth extension** [2505.21198].

A second line emphasizes **multi-stage fusion**. **FUSE** combines a **Sparse Compression Network**, a token-based generative refinement stage, and a final fusion network, augmented by a shift trick and output blending; the paper states that this system **achieved third rank in the URGENT 2025 challenge** [2506.00809]. In its blind-test comparison among the top three systems, FUSE reports the highest **DNSMOS**, **NISQA**, **UTMOS**, and **MOS**, while remaining weaker than the best discriminative model on several intrusive metrics [2506.00809]. A more deployment-oriented variant is **DeepFilterGAN**, a full-band real-time system with **3.45M inference parameters**, **20 ms** window, **10 ms** hop, **2-frame look-ahead**, and **40 ms algorithmic latency**, explicitly described as a 2025 URGENT challenge participant [2505.23515].

The 2026 papers reinforce the same architectural convergence toward **generative–predictive fusion**. The 2026 challenge overview states that the strongest Track 1 systems mostly used **hybrid generative + discriminative paradigms**, often dual-branch or multi-stage, and that successful teams emphasized **MOS-based filtering** of training data and quality-aware curation [2601.13531]. Representative systems include **GAP-URGENet**, which combines a generative branch built from **DeWavLM-Omni**, **Adapter**, and **Vocoder** with a predictive **TF-GridNet** branch and a **PostNet** for learned fusion and bandwidth extension. That system reports **567.76M parameters**, **472.84 GMACs per second**, and validation metrics of **DNSMOS 3.31**, **NISQA 3.96**, **UTMOS 3.22**, **SCOREQ 4.03**, **PESQ 2.89**, **ESTOI 0.90**, **SBS 0.91**, **LPS 0.89**, and **SpkSim 0.82**, and it achieved **1st place in the objective evaluation** on the ICASSP 2026 blind test [2604.01832]. Another 2026 submission, “A Hybrid Discriminative and Generative System for Universal Speech Enhancement,” combines **sampling-frequency-independent TF-GridNet**, an autoregressive generative branch with spectral mapping, and TF-domain fusion, and it **ranked third place** in Track 1 [2601.19113]. In parallel, **UniPASE** extends the low-hallucination PASE framework with **DeWavLM-Omni**, an acoustic **Adapter**, a neural **Vocoder**, and a **PostNet**; the full UniPASE stack reports **545.7M parameters** and **79.2 GMAC/s**, and the paper states that a simple hybrid extension built from UniPASE and predictive **TF-GridNet** achieved **1st place in the objective evaluation** of URGENT 2026 [2604.14606].

## 6. Evaluation controversies, data curation, and recurrent research lessons

One of the most influential later papers is the multilingual evaluation study “P.808 Multilingual Speech Enhancement Testing: Approach and Results of URGENT 2025 Challenge” [2507.11306]. It formalizes the crowdsourced **ITU-T P.808** ACR pipeline for multilingual MOS testing and localizes it to **English**, **German**, **Chinese**, and **Japanese**. The challenge MOS uses **eight ratings per utterance**, and the paper reports first-stage acceptance rates of **82.3%** for English, **62.8%** for German, **41.1%** for Chinese, and **28.9%** for Japanese [2507.11306]. Its most important result is that the language ordering by **MOS** matches the ordering by the phone-fidelity metric
\[
\mathrm{LPS} = 1 - \mathrm{LPD},
\]
but not the ordering by **ESTOI** or the reference-free metrics [2507.11306]. The paper highlights **Japanese** as the clearest mismatch case: **MOS 2.94**, **LPS 0.53**, yet **DNSMOS 2.88** and **NISQA 3.08** [2507.11306]. At the model level, the generative **model #13** reached **MOS 3.34 ± 0.05**, **DNSMOS 3.13**, and **NISQA 3.79**, while collapsing on **ESTOI 0.53** and **LPS 0.58 ± 0.03**; the authors describe the resulting outputs as exhibiting a “high degree of hallucination” [2507.11306]. The paper’s conclusion is not that MOS is obsolete, but that **reference-free subjective ACR MOS and common reference-free objective metrics may jointly fail to detect hallucinations**, so they should be accompanied by **phone-fidelity metrics** such as **LPS** and, where possible, native listeners [2507.11306].

A second major line of critique concerns training targets and data quality. The 2026 paper “Rethinking Training Targets, Architectures and Data Quality for Universal Speech Enhancement” argues that the conventional dereverberation target of **early-reflected speech** is suboptimal and that **time-shifted anechoic clean speech** is a better target [2603.02641]. On the URGENT 2025 non-blind test set, its preferred configuration, **shifted anechoic + GAN**, reports **DNSMOS 3.26**, **NISQA 4.12**, **UTMOS 2.80**, and **CAcc 89.88** [2603.02641]. The same paper also argues that training on large uncurated corpora imposes a performance ceiling, and it uses **VQScore** filtering to show that moderate quality filtering gives a better tradeoff than either no filtering or aggressive pruning [2603.02641]. This concern aligns with the 2024 lessons paper on bandwidth mismatch and noisy labels [2506.01611] and with the 2025 overview’s observation that simply scaling to **~60k hours** in Track 2 did **not** produce a system that surpassed the best Track 1 submission [2505.23212].

Taken together, these studies show that URGENT is not merely a leaderboard of enhancement models. It has become a testbed for unresolved questions about what speech enhancement should optimize, how challenge data should be curated, and how systems should be ranked when perceptual quality, intelligibility, linguistic fidelity, and speaker preservation are not interchangeable [2507.11306][2603.02641][2506.01611]. A plausible implication is that the challenge’s long-term significance lies as much in its evaluation methodology and dataset governance as in any single winning architecture.

Source: https://www.emergentmind.com/topics/urgent-speech-enhancement-challenge