A System for Real-Time Deep Speech Denoising

Recorded speech is often mixed with a variety of background noises, such as a leaf blower, washing machine, dog barking, baby crying, kitchen noises, etc. Background noise significantly degrades the quality and intelligibility of the perceived speech.
In this project, we present a real-time single channel audio denoising deep learning solution, based on recurrent neural networks. Three algorithms were chosen for this purpose: DCCRN, FullSubnet and one that we proposed which is a mix of the two: Complex-FullSubnet.
We’ve trained and integrated all 3 algorithms into a real time speech denoising infrastructure and adjusted them to run in a real time environment.
Finally, we provide performance analysis comparison between the different algorithms using various evaluation method, as well as spectrogram view of the results.

man speaking on the phone