2 papers
eess.AS2022
Spatial Loss for Unsupervised Multi-channel Source Separation
Kohei Saijo, Robin Scheibler
We propose a spatial loss for unsupervised multi-channel source separation. The proposed loss exploits the duality of direction of arrival (DOA) and beamforming: the steering and b…
eess.AS2022
Remix-cycle-consistent Learning on Adversarially Learned Separator for Accurate and Stable Unsupervised Speech Separation
Kohei Saijo, Tetsuji Ogawa
A new learning algorithm for speech separation networks is designed to explicitly reduce residual noise and artifacts in the separated signal in an unsupervised manner. Generative…