Browse State-of-the-Art › Speech Denoising
Speech Denoising
32 papers with code · 2 benchmarks · 3 datasets archive 2025-07-28
Obtain the clean speech of the target speaker by suppressing the background noise. Recent representative github platform ClearerVoice-Studio
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
2 leaderboard tables shown for this task, 2 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| LRS2+VGGSound (1 row) | (unnamed in the archive) | Visual Speech Enhancement Without A Real Visual Stream | code | — | Compare |
| LRS3+VGGSound (1 row) | (unnamed in the archive) | Visual Speech Enhancement Without A Real Visual Stream | code | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
3 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Papers archive 2025-07-28
archive papers tagged: 65 · with a code link: 32 · where Syntology ran a sample: 5 (5 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (5 of 65 tagged: 5 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 65 of 65, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
26 Oct 2021 9 repositories listedSelf-supervised learning (SSL) achieves great success in speech recognition, while limited exploration has been attempted for other speech processing tasks.
-
6 Apr 2020 5 repositories listedIn WaveCRN, the speech locality feature is captured by a convolutional neural network (CNN), while the temporal sequential property of the locality feature is modeled by stacked simple recurrent units (SRU).
-
27 Jun 2018 5 repositories listed Syntology 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 6 harvested samples)We present an end-to-end deep learning approach to denoising speech signals by processing the raw waveform directly.
-
22 Sep 2022 2 repositories listedRather than focusing exclusively on the speech denoising task, we extend this work to address the dereverberation and super-resolution tasks.
-
8 Aug 2022 2 repositories listed Syntology community repositories only · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)The training of modern speech processing systems often requires a large amount of simulated room impulse response (RIR) data in order to allow the systems to generalize well in real-world, reverberant environments.
-
8 Apr 2021 2 repositories listedThis paper tackles the problem of the heavy dependence of clean speech data required by deep learning based audio-denoising methods by showing that it is possible to train deep speech denoising networks using only noisy…
-
3 Feb 2021 2 repositories listedIn this paper, we propose a complex convolutional block attention module (CCBAM) to boost the representation power of the complex-valued convolutional layers by constructing more informative features.
-
27 Jun 2018 2 repositories listedWe present an end-to-end deep learning approach to denoising speech signals by processing the raw waveform directly.
-
13 Feb 2015 2 repositories listedIn this paper, we explore joint optimization of masking functions and deep recurrent neural networks for monaural source separation tasks, including monaural speech separation, monaural singing voice separation, and…
-
14 Oct 2024 1 repository listedThis paper presents CleanUMamba, a time-domain neural network architecture designed for real-time causal audio denoising directly applied to raw waveforms.
-
7 Oct 2024 1 repository listedIn recent years, deep learning-based methods have significantly improved speech enhancement performance, but they often come with a high computational cost, which is prohibitive for a large number of edge devices, such…
-
24 Sep 2024 1 repository listedThe proposed method is evaluated on multiple speech restoration tasks, including speech denoising, bandwidth extension, codec artifact removal, and target speaker extraction.
-
17 Aug 2023 1 repository listed Syntology 13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified (of 14 harvested samples) · 1 pointer-only (licence)Compared to existing phase-aware speech enhancement methods, it further mitigates the compensation effect between the magnitude and phase by explicit phase estimation, elevating the perceptual quality of enhanced speech.
-
3 Mar 2023 1 repository listedExperiments show that Miipher (i) is robust against various audio degradation and (ii) enable us to train a high-quality text-to-speech (TTS) model from restored speech samples collected from the Web.
-
4 Nov 2022 1 repository listedIn this paper, we systematically compare the performance of generative diffusion models and discriminative approaches on different speech restoration tasks.
-
20 Oct 2022 1 repository listedThe proposed RTS target suppresses reverberation and meanwhile maintains the exponential decaying property of reverberation, which will ease the network training, and thus reduce signal distortion caused by the…
-
18 Oct 2022 1 repository listedAudio denoising has been explored for decades using both traditional and deep learning-based methods.
-
12 Apr 2022 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified (of 5 harvested samples) · 2 pointer-only (licence)Speech restoration aims to remove distortions in speech signals.
-
15 Feb 2022 1 repository listedIn this work, we present CleanUNet, a causal speech denoising model on the raw waveform.
-
27 Dec 2021 1 repository listedDeveloping a single-microphone speech denoising or dereverberation front-end for robust automatic speaker verification (ASV) in noisy far-field speaking scenarios is challenging.
-
30 Oct 2021 1 repository listedThe first module adopts a random audio sub-sampler on each noisy audio to generate training pairs.
-
15 Feb 2021 1 repository listedWe describe a modulation-domain loss function for deep-learning-based speech enhancement systems.
-
20 Dec 2020 1 repository listedIn this work, we re-think the task of speech enhancement in unconstrained real-world environments.
-
21 Nov 2020 1 repository listedContemporary speech enhancement predominantly relies on audio transforms that are trained to reconstruct a clean speech waveform.
-
22 Oct 2020 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 4 samples that ran constructed an object rather than computing a result (of 6 harvested samples) · 6 pointer-only (licence)We introduce a deep learning model for speech denoising, a long-standing challenge in audio analysis arising in numerous applications.
-
22 Oct 2020 1 repository listedUsing auxiliary models one at a time, we find acoustic event and self-supervised model PASE+ to be most effective.
-
1 Jun 2020 1 repository listedIn this work, we tackle a denoising and dereverberation problem with a single-stage framework.
-
16 May 2020 1 repository listedIn this paper, we investigate a deep learning approach for speech denoising through an efficient ensemble of specialist neural networks.
-
14 Feb 2020 1 repository listedSpeech enhancement tasks have seen significant improvements with the advance of deep learning technology, but with the cost of increased computational complexity.
-
16 Apr 2019 1 repository listedThe method is completely unsupervised and only trains on the specific audio clip that is being denoised.
-
22 Oct 2018 1 repository listed
-
15 Sep 2017 1 repository listed
-
Active Speech Enhancement: Active Speech Denoising Decliping and Deveraberation22 May 2025 0 repositories listed
-
Knowledge Distillation for Speech Denoising by Latent Representation Alignment with Cosine Distance6 May 2025 0 repositories listed
-
Are Deep Speech Denoising Models Robust to Adversarial Noise?14 Mar 2025 0 repositories listed
-
22 Jan 2025 0 repositories listed
-
TouchTTS: An Embarrassingly Simple TTS Framework that Everyone Can Touch11 Dec 2024 0 repositories listed
-
DENOASR: Debiasing ASRs through Selective Denoising22 Oct 2024 0 repositories listed
-
5 Sep 2024 0 repositories listed
-
22 Jul 2024 0 repositories listed
-
An Investigation of Noise Robustness for Flow-Matching-Based Zero-Shot TTS9 Jun 2024 0 repositories listed
-
Super Denoise Net: Speech Super Resolution with Noise Cancellation in Low Sampling Rate Noisy Environments9 Oct 2023 0 repositories listed
-
uSee: Unified Speech Enhancement and Editing with Conditional Diffusion Models2 Oct 2023 0 repositories listed
-
Complexity Scaling for Speech Denoising14 Sep 2023 0 repositories listed
-
12 Sep 2023 0 repositories listed
-
Target Speech Extraction with Conditional Diffusion Model8 Aug 2023 0 repositories listed
-
A Multi-Stage Triple-Path Method for Speech Separation in Noisy and Reverberant Environments7 Mar 2023 0 repositories listed
-
Speech Enhancement with Multi-granularity Vector Quantization16 Feb 2023 0 repositories listed
-
Speech Dereverberation with A Reverberation Time Shortening Target19 Apr 2022 0 repositories listed
-
FB-MSTCN: A Full-Band Single-Channel Speech Enhancement Method Based on Multi-Scale Temporal Convolutional Network15 Mar 2022 0 repositories listed
-
The PCG-AIID System for L3DAS22 Challenge: MIMO and MISO convolutional recurrent Network for Multi Channel Speech Enhancement and Speech Recognition21 Feb 2022 0 repositories listed
-
Multi-Channel Speech Denoising for Machine Ears17 Feb 2022 0 repositories listed
-
S-DCCRN: Super Wide Band DCCRN with learnable complex feature for speech enhancement16 Nov 2021 0 repositories listed
-
Spark Deficient Gabor Frames for Inverse Problems13 Oct 2021 0 repositories listed
-
Perceptual-based deep-learning denoiser as a defense against adversarial attacks on ASR systems12 Jul 2021 0 repositories listed
-
Incorporating Multi-Target in Multi-Stage Speech Enhancement Model for Better Generalization9 Jul 2021 0 repositories listed
-
Zero-Shot Personalized Speech Enhancement through Speaker-Informed Model Selection8 May 2021 0 repositories listed
-
Learning robust speech representation with an articulatory-regularized variational autoencoder7 Apr 2021 0 repositories listed
-
TSTNN: Two-stage Transformer based Neural Network for Speech Enhancement in the Time Domain18 Mar 2021 0 repositories listed
-
Improving Speech Enhancement Performance by Leveraging Contextual Broad Phonetic Class Information15 Nov 2020 0 repositories listed
-
Simultaneous Denoising and Dereverberation Using Deep Embedding Features6 Apr 2020 0 repositories listed
-
A Review of Multi-Objective Deep Learning Speech Denoising Methods26 Mar 2020 0 repositories listed
-
AeGAN: Time-Frequency Speech Denoising via Generative Adversarial Networks21 Oct 2019 0 repositories listed
-
Speech denoising by parametric resynthesis2 Apr 2019 0 repositories listed
-
Deep Speech Denoising with Vector Space Projections27 Apr 2018 0 repositories listed
Syntology lines on 5 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections