Open qiansichong opened 3 years ago
Sorry I just noticed your issue and really thanks for your correction. It's indeed a mistake. The idea of jointly-diagonaliztion seems good to model the reverberation, but the performance of FastMNMF is not ideal compared to the results in published paper. It is really confused.
https://github.com/KyleZhang1118/Voice-Separation-and-Enhancement/blob/4e98a2a6cb7d860cabe0b4cb2c2c8c122a11bb52/Process_FastMNMF2.m#L104