SOTAVerified

Speech Denoising

Obtain the clean speech of the target speaker by suppressing the background noise. Recent representative github platform ClearerVoice-Studio

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 65 papers

TitleStatusHype
VoiceFixer: A Unified Framework for High-Fidelity Speech RestorationCode3
WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech ProcessingCode3
Explicit Estimation of Magnitude and Phase Spectra in Parallel for High-Quality Speech EnhancementCode2
Speech Denoising in the Waveform Domain with Self-AttentionCode2
Towards Ultra-Low-Power Neuromorphic Speech Enhancement with Spiking-FullSubNetCode2
CMGAN: Conformer-Based Metric-GAN for Monaural Speech EnhancementCode2
Monaural Speech Enhancement with Complex Convolutional Block Attention Module and Joint Time Frequency LossesCode2
FRA-RIR: Fast Random Approximation of the Image-source MethodCode2
Speech Denoising with Auditory ModelsCode1
Speech Denoising with Deep Feature LossesCode1
Visual Speech Enhancement Without A Real Visual StreamCode1
CleanUMamba: A Compact Mamba Network for Speech Denoising using Channel PruningCode1
Miipher: A Robust Speech Restoration Model Integrating Self-Supervised Speech and Text RepresentationsCode1
Self-Supervised Speech Denoising Using Only Noisy Audio SignalsCode1
WaveCRN: An Efficient Convolutional Recurrent Neural Network for End-to-end Speech EnhancementCode1
BirdSoundsDenoising: Deep Visual Audio Denoising for Bird SoundsCode1
Listening to Sounds of Silence for Speech DenoisingCode1
Speech Denoising by Accumulating Per-Frequency Modeling FluctuationsCode1
A Modulation-Domain Loss for Neural-Network-based Real-time Speech EnhancementCode1
Speech Denoising Without Clean Training Data: A Noise2Noise ApproachCode1
Perceptual Loss based Speech Denoising with an ensemble of Audio Pattern Recognition and Self-Supervised ModelsCode0
Sparse Mixture of Local Experts for Efficient Speech EnhancementCode0
Speech Denoising Convolutional Neural Network trained with Deep Feature Losses.Code0
Phase-aware Single-stage Speech Denoising and Dereverberation with U-NetCode0
Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source SeparationCode0
Show:102550
← PrevPage 1 of 3Next →
All datasetsLRS2+VGGSoundLRS3+VGGSound

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CBAK2.41—Unverified
#ModelMetricClaimedVerifiedStatus
1CBAK2.47—Unverified