|
ROSE-CD(PESQ)
|
Robust One-step Speech Enhancement via Consistenc…
|
3.99
|
2025-07-08
|
|
|
PESQetarian
|
The PESQetarian: On the Relevance of Goodhart's L…
|
3.82
|
2024-06-05
|
|
|
Mamba-SEUNet L (+PCS)
|
Mamba-SEUNet: Mamba UNet for Monaural Speech Enha…
|
3.73
|
2024-12-21
|
|
|
Schrödinger bridge (PESQ loss)
|
Investigating Training Objectives for Generative …
|
3.70
|
2024-09-16
|
|
|
SEMamba (+PCS)
|
An Investigation of Incorporating Mamba for Speec…
|
3.69
|
2024-05-10
|
|
|
PrimeK-Net
|
PrimeK-Net: Multi-scale Spectral Learning via Gro…
|
3.61
|
2025-02-27
|
|
|
MP-SENet
|
Explicit Estimation of Magnitude and Phase Spectr…
|
3.60
|
2023-08-17
|
|
|
xLSTM-SENet2
|
xLSTM-SENet: xLSTM for Single-Channel Speech Enha…
|
3.53
|
2025-01-10
|
|
|
SCP-CMGAN
|
SCP-GAN: Self-Correcting Discriminator Optimizati…
|
3.52
|
2022-10-26
|
|
|
ROSE-CD
|
Robust One-step Speech Enhancement via Consistenc…
|
3.49
|
2025-07-08
|
|
|
D2Former
|
Monaural Speech Enhancement with Complex Convolut…
|
3.43
|
2021-02-03
|
|
|
CMGAN
|
CMGAN: Conformer-Based Metric-GAN for Monaural Sp…
|
3.41
|
2022-09-22
|
|
|
PCS
|
Perceptual Contrast Stretching on Target Feature …
|
3.35
|
2022-03-31
|
|
|
aTENNuate
|
aTENNuate: Optimized Real-time Speech Enhancement…
|
3.27
|
2024-09-05
|
|
|
Centaurus (0.51M)
|
Let SSMs be ConvNets: State-space Modeling with O…
|
3.25
|
2025-01-22
|
|
|
MANNER
|
MANNER: Multi-view Attention Network for Noise Er…
|
3.21
|
2022-03-04
|
|
|
BSSE-SE
|
Boosting Self-Supervised Embeddings for Speech En…
|
3.20
|
2022-04-07
|
|
|
DeepFilterNet3
|
DeepFilterNet: Perceptually Motivated Real-Time S…
|
3.17
|
2023-05-14
|
|
|
PERL-AE
|
Perceptual Loss based Speech Denoising with an en…
|
3.17
|
2020-10-22
|
|
|
PFPL
|
Improving Perceptual Quality by Phone-Fortified P…
|
3.15
|
2020-10-28
|
|
|
MetricGAN+
|
MetricGAN+: An Improved Version of MetricGAN for …
|
3.15
|
2021-04-08
|
|
|
MANNER-S + MV-AT (8.1GF)
|
Multi-View Attention Transfer for Efficient Speec…
|
3.12
|
2022-08-22
|
|
|
SGMSE+
|
An Analysis of the Variance of Diffusion-based Sp…
|
3.11
|
2024-02-01
|
|
|
DEMUCS (H=64, S=2 ,U =2)
|
Real Time Speech Enhancement in the Waveform Doma…
|
3.07
|
2020-06-23
|
|
|
Dense-TSNet
|
Dense-TSNet: Dense Connected Two-Stage Structure …
|
3.05
|
2024-09-18
|
|
|
RDL-Net 3.91M (Deep Xi - MMSE-LSA)
|
Deep Residual-Dense Lattice Network for Speech En…
|
3.02
|
2020-02-27
|
|
|
ROSE
|
ROSE: A Recognition-Oriented Speech Enhancement F…
|
3.01
|
2023-12-11
|
|
|
RDL-Net 3.91M (Deep Xi - SRWF)
|
Deep Residual-Dense Lattice Network for Speech En…
|
2.94
|
2020-02-27
|
|
|
RDL-Net 1.87M (Deep Xi - MMSE-LSA)
|
Deep Residual-Dense Lattice Network for Speech En…
|
2.93
|
2020-02-27
|
|
|
Causal DEMUCS (H=48,S=4, U =4)
|
Real Time Speech Enhancement in the Waveform Doma…
|
2.93
|
2020-06-23
|
|
|
SGMSE+ (Diffusion Model)
|
Speech Enhancement and Dereverberation with Diffu…
|
2.93
|
2022-08-11
|
|
|
MetricGAN
|
MetricGAN: Generative Adversarial Networks based …
|
2.86
|
2019-05-13
|
|
|
RDL-Net 1.87M (Deep Xi - SRWF)
|
Deep Residual-Dense Lattice Network for Speech En…
|
2.84
|
2020-02-27
|
|
|
real-time-GRU
|
A Modulation-Domain Loss for Neural-Network-based…
|
2.82
|
2021-02-15
|
|