SA-SDR: A Novel Loss Function for Separation of Meeting Style Data von Neumann, Thilo Kinoshita, Keisuke Boeddeker, Christoph Delcroix, Marc Haeb-Umbach, Reinhold ddc:000 IEEE 2022 info:eu-repo/semantics/conferenceObject doc-type:conferenceObject text http://purl.org/coar/resource_type/c_5794 https://ris.uni-paderborn.de/record/33819 https://ris.uni-paderborn.de/download/33819/33820 https://ris.uni-paderborn.de/download/33819/33821 von Neumann T, Kinoshita K, Boeddeker C, Delcroix M, Haeb-Umbach R. SA-SDR: A Novel Loss Function for Separation of Meeting Style Data. In: <i>ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</i>. IEEE; 2022. doi:<a href="https://doi.org/10.1109/icassp43922.2022.9746757">10.1109/icassp43922.2022.9746757</a> eng info:eu-repo/semantics/altIdentifier/doi/10.1109/icassp43922.2022.9746757 info:eu-repo/grantAgreement/EC/448568305 info:eu-repo/semantics/openAccess