Real-time noise cancellation

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) H100
• DeepStream Version 7
• TensorRT Version 9
**• Issue Type ** Question

So I want to build a pipeline for real-time audio streaming and having a hard time locating the specific plugin to use for audio input. Also if someone has a sample for noise suppression pipeline it would be really appreciated.

The audio sample app does it from a wav file, but I want to do it for live streaming audio (either through microphone or over the network (think phone calls)).

3

Do you mean the telephony voice call?

4

Sorry for taking a while to reply,
I mean WhatsAppy calls (VOIP) use cases. I was reading up on Maxine and found out its not supported by H100. Also if you could give me the idea of a basic pipeline for deepstream for audio processing that would be great.

The way I see it as (very high level)

RTP source → audio decode → audio transform?? → nvds-inferaudio → audio encode → rtp payload?

I didnt find much documentation to that effect so if you can point me in the right direction, would be great.

thanks !

5

The pipeline is OK.

DeepStream provides samples of audio inferencing pipeline. DeepStream Reference Application - deepstream-audio app — DeepStream documentation 6.4 documentation

1 Like
6

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.