Flock’s Gunshot Detection Microphones Will Start Listening for Human Voices (www.eff.org)
from ExtremeDullard@piefed.social to privacy@lemmy.ml on 06 Oct 22:52
https://piefed.social/post/1342461

#privacy

threaded - newest

panda_abyss@lemmy.ca on 06 Oct 23:54 next collapse

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.

First_Thunder@lemmy.zip on 07 Oct 00:29 next collapse

Wait, how? Got a link pls?

Sylvartas@lemmy.dbzer0.com on 07 Oct 01:37 next collapse

My bet is on some Fourier transform fuckery

panda_abyss@lemmy.ca on 07 Oct 03:45 collapse

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.

harsh3466@lemmy.ml on 07 Oct 01:20 collapse

ELI5 please?

PiraHxCx@lemmy.ml on 07 Oct 00:09 next collapse

I want a “target pressure wave attack” necklace

excursion22@piefed.ca on 07 Oct 00:39 next collapse

No one could’ve ever seen this coming…

ms_lane@lemmy.world on 07 Oct 04:36 next collapse

Does this mean the people playing their crappy music at full blast on speakers as they walk are now providing a public service?

AfricanExpansionist@lemmy.ml on 07 Oct 12:16 next collapse

Flood them with signal so that it’s all noise

thegreekgeek@midwest.social on 07 Oct 15:11 collapse

Oh no, who could have possibly foreseen that this was their endgame?