Real Time Noise cancellatio in audio

I want to build an application which takes a live audio from source(mic) and filtering the noise(unwanted sounds like chattering, traffic noises) and fetch into and application for further processing.

I want to apply Machine Learning Framework(TensorFlow, Keras) and Deep Learning neural Networks(i.e RNN) for filtering the noise from the audio. I want to do this in a real time environment. My inference device will be a Nvidia Jetson Devices. Please guide me where I can find the related documents and how to proceed with the project.

If there is any solution available in any website please refer me the link.

TensorFlow and TensorRT are tools that may be useful to you and are available for NVIDIA Jetson. TensorFlow installation is documented here https://docs.nvidia.com/deeplearning/frameworks/install-tf-jetson-platform/index.html. TensorRT is available as part of the Jetson Jetpack https://docs.nvidia.com/jetson/index.html.

Advice on specific Deep Learning model architectures for noise filtering falls beyond the scope of this forum.