I had to do a bit of research to remind myself. We did this in university as an exercise, so it was a while ago.
Basically with N signals (speakers) and M mixes (microphones). When M > N then you can create an MxN matrix and solve it numerically, and we were able to do that pretty easily. We also did the case where M=N as a demo and we used ICA for that with either projection pursuit or SVD, I can’t remember.
With modern models this would be even easier with fewer microphones, and there’s been a lot of time and money between when these methods were devised and now.
threaded - newest
Here’s a fun trick: If you have N microphones on an area you can filter the audio to N -1 voices using just linear algebra, no AI.
It’s a very cool trick.
Now imagine what happens when you add AI and blanket an area.
Wait, how? Got a link pls?
My bet is on some Fourier transform fuckery
I had to do a bit of research to remind myself. We did this in university as an exercise, so it was a while ago.
Basically with N signals (speakers) and M mixes (microphones). When M > N then you can create an MxN matrix and solve it numerically, and we were able to do that pretty easily. We also did the case where M=N as a demo and we used ICA for that with either projection pursuit or SVD, I can’t remember.
You can read more about this on Wikipedia:
With modern models this would be even easier with fewer microphones, and there’s been a lot of time and money between when these methods were devised and now.
ELI5 please?
I want a “target pressure wave attack” necklace
No one could’ve ever seen this coming…
Does this mean the people playing their crappy music at full blast on speakers as they walk are now providing a public service?
Flood them with signal so that it’s all noise
Oh no, who could have possibly foreseen that this was their endgame?