• Welcome to TechPowerUp Forums, Guest! Please check out our forum guidelines for info related to our community.
  • The forums have been upgraded with support for dark mode. By default it will follow the setting on your system/browser. You may override it by scrolling to the end of the page and clicking the gears icon.

AMD Readies Noise Suppression Software to Rival RTX Voice

btarunr

Editor & Senior Moderator
Staff member
Joined
Oct 9, 2007
Messages
47,853 (7.39/day)
Location
Dublin, Ireland
System Name RBMK-1000
Processor AMD Ryzen 7 5700G
Motherboard Gigabyte B550 AORUS Elite V2
Cooling DeepCool Gammax L240 V2
Memory 2x 16GB DDR4-3200
Video Card(s) Galax RTX 4070 Ti EX
Storage Samsung 990 1TB
Display(s) BenQ 1440p 60 Hz 27-inch
Case Corsair Carbide 100R
Audio Device(s) ASUS SupremeFX S1220A
Power Supply Cooler Master MWE Gold 650W
Mouse ASUS ROG Strix Impact
Keyboard Gamdias Hermes E2
Software Windows 11 Pro
AMD is readying a Noise Suppression software to go with future updates to AMD Software Adrenalin. A rival to NVIDIA RTX Voice, the software cancels background noise both from your microphone, as well as from the person on the other side of the line, in a voice chat. It does so by isolating voices from sounds it interprets as background noise or sounds uncharacteristic of voices.

Much like NVIDIA, AMD is relying on a "real-time deep-learning algorithm" to identify and isolate human voices from an audio stream, although the company wouldn't say how the AI is being accelerated on the hardware. Since AMD Noise Suppression is being distributed through the Adrenalin package, it's reason to believe that you'll need an AMD Radeon GPU (either discrete or integrated), to use the software.



View at TechPowerUp Main Site | Source
 
Those AI-upscaled images tho...

Still, great to see alternatives to NVIDIA's proprietary bullshit popping up. Any word on if it's open-source?
 
Last edited:
If they are now trying to get even on the streaming software extras, it means they may finally make their encoding to rival nvenc.
 
Honestly, as much as I hate to say it because I dislike running 1 off random apps. I use a schiit hel 2, paired with a AT-BP40 and I pass my mic through nvbroadcast with echo reduction and noise removal, and honestly it does a fantastic job.
 
Last edited:
Cool!

All we need now is an AMD equivalent to Nvidia Canvas to believe that Nvidia's Tensor cores actually don't do anything.
 
Cool!

All we need now is an AMD equivalent to Nvidia Canvas to believe that Nvidia's Tensor cores actually don't do anything.
I don't disagree, but I haven't seen much use of it since the presentation. The scope of people that need it and will buy an AMD card because of it, is small if non-existing.
 
I'm totally out of the loop on this stuff, but why is this a video card responsibility?
See it as a type of task a GPU is just potentially good/efficient at.
 
RTX voice is an amazing piece of software. It's why I went with a Nvidia GPU config on my Laptop because of the Ai noise cancellation.
 
As long as it doesnt blow out ram usage like Nvidias software does

Good option to exist, at least
 
RTX voice is an amazing piece of software. It's why I went with a Nvidia GPU config on my Laptop because of the Ai noise cancellation.
Isn't software / Teams just as good at it right now? Noise is never an issue anywhere and hasn't been for the better part of 5 years now.

As in, pretty much flawless
And it doesn't require your GPU to run an actual load in an actual Pstate above idle. Because it does.
 
So now both GPU manufacturers have legit reason to access microphones, what a progress.

The last time things were as exciting, was with webex.
Webex just happens to give you that comfort of "listening to ultrasound" to hear some devices that might emit it to "connect".
Hence listening to mic non-stop.

Luckily though, it could be switched off.
 
Noise is never an issue anywhere and hasn't been for the better part of 5 years now.
:roll:
There are many application that will require background noise suppression, video chat is just one of numerous applications were it can be used.
Teams does not have anything to do with how I use RTX voice. Best not assume that everyone's usage is the same has yours.
 
Last edited:
Honestly, as much as I hate to say it because I dislike running 1 off random apps. I use a schiit hel 2, paired with a AT-BP40 and I pass my mic through nvbroadcast with echo reduction and noise removal, and honestly it does a fantastic job.

There's a VST plugin option if what you're using supports that


Cool!

All we need now is an AMD equivalent to Nvidia Canvas to believe that Nvidia's Tensor cores actually don't do anything.

Hopefully they'll only rely on common instructions like dp4a and make it open enough that it can be used on anything further bringing the heat to nvidia's habit of making everything exclusive and proprietary
 
Cool!

All we need now is an AMD equivalent to Nvidia Canvas to believe that Nvidia's Tensor cores actually don't do anything.
I though that it was already known that you can run A.I stuff on classic hardware, but it would just be less efficient to do so. Even Intel and AMD also have their own "tensor" core on some CPU and GPU
 
amd marketing team is going downhill
 
:roll:
There are many application that will require background noise suppression, video chat is just one of numerous applications were it can be used.
Teams does not have anything to do with how I use RTX voice. Best not assume that everyone's usage is the same has yours.
How do you use it? I'm curious, as I was when you pointed it out a post earlier :)
 
How do you use it? I'm curious, as I was when you pointed it out a post earlier :)
I use the background noise cancellation in Audacity mostly and well as in Davinci resolve for recording audio in an extremely noisy enviroment.

The original plan was to make a sound proof room for recording Audio because of the high daily noise where I am. It was relatively expensive to do this
and RTX voice is basically free so great "cheap" solution provided you have a Nvidia GPU.
 
How do you use it? I'm curious, as I was when you pointed it out a post earlier :)
It's great for discord, to remove MX blue clicky clacky and heavy mouth breathers

Of course, you need the noisy party to have it enabled so it's not helpful if they're ignorant of the fact they're loud AF
 
I though that it was already known that you can run A.I stuff on classic hardware, but it would just be less efficient to do so. Even Intel and AMD also have their own "tensor" core on some CPU and GPU
You probably can, but Canvas is an nvidia software that only runs on nvidia cards.
 
Is anyone able to use RTX voice/broadcast to remove noise from simple video files like mkv, avi, mp4 etc? I could swear it used to work for me back when it was RTX voice but at some point it broke and no longer removes noise from all sources.
 
Is anyone able to use RTX voice/broadcast to remove noise from simple video files like mkv, avi, mp4 etc? I could swear it used to work for me back when it was RTX voice but at some point it broke and no longer removes noise from all sources.
That had two modes - one for input one for output

You might be confusing the output method for actually altering the files?
 
Back
Top