Researchers have used AI attached to off-the-shelf headphones to isolate the voice of one speaker in a noisy crowd just by looking at them. The code for their next-level noise cancelling system is freely available if you want to build your own.
I think once it has taken a profile of the voice it no longer requires you to be facing the person because it can now recognize that voice among the noise. The AI but is taking an imprint of the voice and then extracting it.
I’m not an expert, but my understanding is that noise cancellation works by inverting sounds waves to deaden the sound. So, like, if you add sin(x) and –sin(x) you get 0.
This system is actively adding inverted sound waves to cancel most sounds. What makes this system unique is that it samples the voice and uses the unique “voice print” to selectively not invert the sound waves from the targeted voice.
Or that’s what I’m getting from reading this, as a layman.
The video fails to explain what about this is “AI” as opposed to active noise cancelling with some regular old signal processing.
I think once it has taken a profile of the voice it no longer requires you to be facing the person because it can now recognize that voice among the noise. The AI but is taking an imprint of the voice and then extracting it.
So, some tracking layered on top of basic beamforming
I legume so
You’re nuts
To add to what the other poster said:
I’m not an expert, but my understanding is that noise cancellation works by inverting sounds waves to deaden the sound. So, like, if you add sin(x) and –sin(x) you get 0.
This system is actively adding inverted sound waves to cancel most sounds. What makes this system unique is that it samples the voice and uses the unique “voice print” to selectively not invert the sound waves from the targeted voice.
Or that’s what I’m getting from reading this, as a layman.