I use Izotope RX 3 denoise almost daily, so that will be my main comparison point. One question that I have now is - why have a focus on speed? Very few applications for denoise need to happen in real time. In fact, quality is paramount as it's usually employed in achieve or production applications.
Ok, I've listed to some samples now. I'm very impressed how good the results are. There are far fewer artefacts when using the new algorithm. I'd love to try this on a vinyl record recording
As strange as it may sound, you should not be expecting an increase in intelligibility.
Just thought this should be of interest to some people here. I just published a demo that shows how you can do better noise suppression using deep learning.
The processing does not seem to be all that exceptional. looks like a strong variable noise gate cascaded with a weaker dynamic equalizer.
Does the deep learning process involve recognizing the main speaker's voice characteristics e.g. formant, or detect the language being used (speech recognition) so that the algorithm can tell the signal and noise apart?
Wasn't lossy compression artificial intelligence, way back then with MP3?