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
Towards Ultra-Low-Power Neuromorphic Speech Enhancement with Spiking-FullSubNetCode2
Explicit Estimation of Magnitude and Phase Spectra in Parallel for High-Quality Speech EnhancementCode2
CMGAN: Conformer-Based Metric-GAN for Monaural Speech EnhancementCode2
FRA-RIR: Fast Random Approximation of the Image-source MethodCode2
Speech Denoising in the Waveform Domain with Self-AttentionCode2
Monaural Speech Enhancement with Complex Convolutional Block Attention Module and Joint Time Frequency LossesCode2
CleanUMamba: A Compact Mamba Network for Speech Denoising using Channel PruningCode1
Miipher: A Robust Speech Restoration Model Integrating Self-Supervised Speech and Text RepresentationsCode1
BirdSoundsDenoising: Deep Visual Audio Denoising for Bird SoundsCode1
Self-Supervised Speech Denoising Using Only Noisy Audio SignalsCode1
Speech Denoising Without Clean Training Data: A Noise2Noise ApproachCode1
A Modulation-Domain Loss for Neural-Network-based Real-time Speech EnhancementCode1
Visual Speech Enhancement Without A Real Visual StreamCode1
Speech Denoising with Auditory ModelsCode1
Listening to Sounds of Silence for Speech DenoisingCode1
WaveCRN: An Efficient Convolutional Recurrent Neural Network for End-to-end Speech EnhancementCode1
Speech Denoising by Accumulating Per-Frequency Modeling FluctuationsCode1
Speech Denoising with Deep Feature LossesCode1
Active Speech Enhancement: Active Speech Denoising Decliping and Deveraberation—0
Knowledge Distillation for Speech Denoising by Latent Representation Alignment with Cosine Distance—0
Are Deep Speech Denoising Models Robust to Adversarial Noise?—0
Let SSMs be ConvNets: State-space Modeling with Optimal Tensor ContractionsCode0
TouchTTS: An Embarrassingly Simple TTS Framework that Everyone Can Touch—0
Show:102550
← PrevPage 1 of 3Next →
All datasetsLRS2+VGGSoundLRS3+VGGSound

Benchmark Results

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