VoiceBank-DEMAND
Emerging47papers using it
2021first seen
VoiceBank-DEMAND is a dataset used to evaluate speech quality by providing diverse audio samples with corresponding perceptual mean opinion scores (MOS).
Papers using VoiceBank-DEMAND (47)
- PrimeK-Net: Multi-scale Spectral Learning via Group Prime-Kernel
Convolutional Neural Networks for Single Channel Speech EnhancementZipEnhancer: Dual-Path Down-Up Sampling-based Zipformer for Monaural
Speech EnhancementQC-GAN: A Parameter-Efficient Quaternion Conformer GAN for High-Fidelity Speech EnhancementPosterior Transition Modeling for Unsupervised Diffusion-Based Speech EnhancementxLSTM-SENet: xLSTM for Single-Channel Speech EnhancementMagnitude-Phase Dual-Path Speech Enhancement Network based on
Self-Supervised Embedding and Perceptual Contrast Stretch BoostingSB-RF: Schr\"odinger Bridge Rectified Flow for One-Step Robust Speech EnhancementG-MaP-SE: Guided Speech Enhancement via GMM-Based Prior MatchingBASENet: Band-Adapted Speech Enhancement Network with Cross-Band AttentionFew-Shot and Pseudo-Label Guided Speech Quality Evaluation with Large Language ModelsSpeech Enhancement Based on Drifting ModelsDiffusion-based Frameworks for Unsupervised Speech EnhancementBeyond Performance: Probing Representation Dynamics In Speech Enhancement ModelsI-DCCRN-VAE: An Improved Deep Representation Learning Framework for Complex VAE-based Single-channel Speech EnhancementMeanFlowSE: one-step generative speech enhancement via conditional mean flowInvestigation of Speech and Noise Latent Representations in Single-channel VAE-based Speech EnhancementEffiFusion-GAN: Efficient Fusion Generative Adversarial Network for Speech EnhancementRobust One-step Speech Enhancement via Consistency DistillationDo We Need EMA for Diffusion-Based Speech Enhancement? Toward a Magnitude-Preserving Network ArchitectureaTENNuate: Optimized Real-time Speech Enhancement with Deep SSMs on Raw AudioCMGAN: Conformer-based Metric GAN for Speech EnhancementMP-SENet: A Speech Enhancement Model with Parallel Denoising of
Magnitude and Phase SpectraMANNER: Multi-view Attention Network for Noise ErasureMetricGAN+/-: Increasing Robustness of Noise Reduction on Unseen DataSingle-Channel Speech Enhancement with Deep Complex U-Networks and
Probabilistic Latent Space ModelsTENET: A Time-reversal Enhancement Network for Noise-robust ASRA General Unfolding Speech Enhancement Method Motivated by Taylor's
TheoremPerceptual Contrast Stretching on Target Feature for Speech EnhancementSCP-GAN: Self-Correcting Discriminator Optimization for Training
Consistency Preserving Metric GAN on Speech Enhancement TasksDiffusion-based Generative Speech Source SeparationTHLNet: two-stage heterogeneous lightweight network for monaural speech
enhancementA Multi-dimensional Deep Structured State Space Approach to Speech
Enhancement Using Small-footprint ModelsSpiking Structured State Space Model for Monaural Speech EnhancementAn Investigation of Incorporating Mamba for Speech EnhancementSpeech enhancement deep-learning architecture for efficient edge
processingBSS-CFFMA: Cross-Domain Feature Fusion and Multi-Attention Speech
Enhancement Network based on Self-Supervised EmbeddingOSSEM: one-shot speaker adaptive speech enhancement using meta learningInvestigating self-supervised learning for speech enhancement and
separationTridentSE: Guiding Speech Enhancement with 32 Global TokensCold Diffusion for Speech EnhancementEfficient Monaural Speech Enhancement using Spectrum Attention FusionMUSE: Flexible Voiceprint Receptive Fields and Multi-Path Fusion
Enhanced Taylor Transformer for U-Net-based Speech EnhancementExploiting Consistency-Preserving Loss and Perceptual Contrast
Stretching to Boost SSL-based Speech EnhancementEffective Noise-aware Data Simulation for Domain-adaptive Speech
Enhancement Leveraging Dynamic Stochastic PerturbationSpeech-Declipping Transformer with Complex Spectrogram and Learnerble
Temporal FeaturesA Neural Denoising Vocoder for Clean Waveform Generation from Noisy
Mel-Spectrogram based on Amplitude and Phase PredictionsFrom KAN to GR-KAN: Advancing Speech Enhancement with KAN-Based Methodology