This is the repo of the manuscript "Embedding and Beamforming: All-Neural Causal Beamformer for Multichannel Speech Enhancement", which is to be submitted to ICASSP2022. The network code has been released and you can train it with your own pipeline. The demo website can be viewed at here.
I have rearranged the network code, so if you find any mistakes during the training, please feel free to tell me!