RTNet
RTNet copied to clipboard
implementation of Monaural Speech Enhancement with Recursive Learning in the Time Domain
Hi andong,your paper use 115 types noise for training and 5 types noise for testing,but i can't get them all,can you send me the 16k librosa concated noise long vector...
Hello, I would like to know which evaluation methods you used for PESQ or STOI? More specfically, whether you use the pystoi and pesq python library for evalution or not?...
Hi! I'd like to reproduce the very good results of your paper. When I run it on a 15,000 samples * 3s dataset, loss only decreases considerably at the very...
Hi Andong, Congrats on your paper ! Maybe you have seen [Asteroid](https://github.com/mpariente/asteroid), an open-source community-based source separation and speech enhancement toolkit. RTNet would be a great fit in Asteroid, it...