214 citations · 243 across the 5 of their papers we have counts for
5 papers
U-PAST: A Phase-Aware Audio Spectrogram Transformer-U-Net for Single-Channel Speech Enhancement
Cao Duong Ly, Jörn Anemüller
Convolutional neural networks (CNNs), used widely and successfully in audio enhancement, capture long-range time-frequency dependencies only indirectly, through successive convolut…
Single-Channel Speech Enhancement with Deep Complex U-Networks and Probabilistic Latent Space Models
Eike J. Nustede, Jörn Anemüller
In this paper, we propose to extend the deep, complex U-Network architecture for speech enhancement by incorporating a probabilistic (i.e., variational) latent space model. The pro…
Towards speech enhancement using a variational U-Net architecture
Eike J. Nustede, Jörn Anemüller
We investigate the viability of a variational U-Net architecture for denoising of single-channel audio data. Deep network speech enhancement systems commonly aim to estimate filter…
Complex Independent Component Analysis of Frequency-Domain Electroencephalographic Data
Jorn Anemuller, Terrence J. Sejnowski, Scott Makeig
Independent component analysis (ICA) has proven useful for modeling brain and electroencephalographic (EEG) data. Here, we present a new, generalized method to better capture the d…
Coupled dynamics of fast spins and slow exchange interactions in the XY spin-glass
G Jongen, J Anemueller, D Bolle +2
We investigate an XY spin-glass model in which both spins and interactions (or couplings) evolve in time, but with widely separated time-scales. For large times this model can be s…