2 code implementations • 24 Jan 2022 • Kilian Schulze-Forster, Gaël Richard, Liam Kelley, Clement S. J. Doire, Roland Badeau
Integrating domain knowledge in the form of source models into a data-driven method leads to high data efficiency: the proposed approach achieves good separation quality even when trained on less than three minutes of audio.
no code implementations • 14 Aug 2019 • Clement S. J. Doire, Olumide Okubadejo
We propose an interleaved training procedure that optimizes the sub-task decoders independently and thus does not require each sample to possess a ground truth for all of its composing sources.