VoiceBank+DEMAND
PulseAugur coverage of VoiceBank+DEMAND — every cluster mentioning VoiceBank+DEMAND across labs, papers, and developer communities, ranked by signal.
-
HybridSB-MoE advances speech enhancement with dual-domain modeling
Researchers have introduced HybridSB-MoE, a novel framework for speech enhancement that addresses limitations in spectral and waveform modeling. This dual-domain approach uses asymmetric uncertainty fusion, allowing spe…
-
RT-SEMamba: New Mamba-based model offers real-time speech enhancement
Researchers have developed RT-SEMamba, a new real-time speech enhancement model utilizing causal time-frequency Mamba blocks. This architecture offers memory and bandwidth efficiency for long-form inference by propagati…
-
New research explores audio-visual and flow-matching techniques for speech enhancement
Two new research papers explore advanced techniques for speech enhancement using generative models. The first paper introduces Audio-visual Contrastive Alignment (AVCA) to improve diffusion-based speech enhancement by e…
-
New QC-GAN offers parameter-efficient speech enhancement
Researchers have developed QC-GAN, a new parameter-efficient framework for speech enhancement that combines a Quaternion Conformer generator with MetricGAN-based training. This approach utilizes the Hamilton product to …
-
New BASENet architecture enhances speech with frequency-adapted processing
Researchers have developed BASENet, a novel speech enhancement network that adapts its processing capacity based on the perceptual importance of different frequency bands. This architecture assigns more resources to low…
-
DriftSE framework offers one-step speech enhancement using generative models
Researchers have introduced DriftSE, a new generative framework for speech enhancement that bypasses iterative sampling for single-step inference. This novel approach formulates denoising as an equilibrium problem, usin…