Mic noise suppression breaks voice-based controls

EvanBalster
Contributor

Mic noise suppression breaks voice-based controls

Hello —

 

(I started an earlier thread in the Audio SDK forum, but this issue is unrelated to spatial audio so I'm posting in general support.)

 

We're making SoundSelf, an accessible voice-driven experience for Vive.  The player interacts with the game by making sustained tonal sounds with their voice.  However, Vive's noise suppression algorithm identifies any sustained sound (>.75s) as background noise, and cuts it (-40-60dB) from the signal.  In our case, this means Vive is deleting player input — making our experience unplayable.

 

Like most voice-recognition technologies, our technology works best with unprocessed audio.  In order to support voice-recognition apps better, Windows 10 includes a "raw mode" in its WASAPI audio API.  Oculus implements raw mode in its mic audio driver, allowing us to easily circumvent its noise suppression.  Vive, however, does not — and I have been unable to find any API call or user preference to do so.

 

This is truly a show-stopping issue for us and we may not be able to ship on Vive if it can't be addressed.  It's like playing a game where all the buttons and joysticks automatically reset to zero every split-second.

Highlighted
EvanBalster
Contributor

Re: Mic noise suppression breaks voice-based controls

In case a driver developer should happen to see this thread, here is the relevant Microsoft documentation:

 

https://docs.microsoft.com/en-us/windows-hardware/drivers/audio/audio-signal-processing-modes

 

Raw mode is listed right at the top of the page.