Annika Briegleb — accepted AI-conference papers

2023

Exploiting Spatial Information with the Informed Complex-Valued Spatial Autoencoder for Target Speaker Extraction

Annika Briegleb, Mhd Modar Halimeh, Walter Kellermann

ICASSP 2023accepted

In conventional multichannel audio signal enhancement, spatial and spectral filtering are often performed sequentially. In contrast, it has been shown that for neural spatial filtering a joint approach of spectro-spatial filtering is more beneficial. In this contribution, we investigate the spatial…

Cited by 0 Source ↗Scholar ↗

2021

Combining Adaptive Filtering And Complex-Valued Deep Postfiltering For Acoustic Echo Cancellation

Mhd Modar Halimeh, Thomas Haubner, Annika Briegleb, Alexander Schmidt, Walter Kellermann

ICASSP 2021accepted

In this contribution, we introduce a novel approach to noise-robust acoustic echo cancellation employing a complex-valued Deep Neural Network (DNN) for postfiltering. In a first step, early linear echo components are removed using a double-talk robust adaptive filter. The residual signal is subseque…

Cited by 0 Source ↗Scholar ↗