Real-Time Noise Suppression Using Deep Learning

Originally published at: https://developer.nvidia.com/blog/nvidia-real-time-noise-suppression-deep-learning/

Imagine waiting for your flight at the airport. Suddenly, an important business call with a high profile customer lights up your phone. Tons of background noise clutters up the soundscape around you — background chatter, airplanes taking off, maybe a flight announcement. You have to take the call and you want to sound clear. We…

The Krisp page says it works for IoT applications. In these scenarios, is it limited to single-mic devices? Many IoT devices are multi-mic, for instance smart speakers? Can these be quickly integrated with Krisp, or do they have to be redesigned to single-mic devices?

If I already have existing noisy sound files, what is the best way to go about de-noising them and extracting the speech per party for use?

I know of two startups that can enhance audio files - https://babblelabs.com/prod... and https://2hz.ai/

Thanks for sharing
This article is all about noise suppression in headphones and telephones. I wonder if there are any experiments about noise cancellation in a room or in a car when you are not wearing a headset? when you are just sitting there and hearing the noise with your plain ears.
Is there a solution for that kind of problems?