Samuele Cornell
@samuelecornell
Post-doc @ CMU LTI. Audio and speech researcher.
ID: 1359140127889588226
https://github.com/popcornell 09-02-2021 14:01:05
167 Tweet
858 Takipçi
516 Takip Edilen
This is a great work from my colleague Zhong-Qiu Wang. IMO it is the first work that does unsupervised **fully neural** (beamforming not required) speech separation in a multi-channel setting without resorting to mixtures of mixtures. Performance is close to supervised PIT.