Flock Safety, the police technology company most notable for their extensive network of automated license plate readers spread throughout the United States, is rolling out a new and troubling product that may create headaches for the cities that adopt it: detection of “human distress” via audio. As...
  • panda_abyss@lemmy.ca
    33·
    9 hours ago

    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.

      • panda_abyss@lemmy.ca
        8·
        5 hours ago

        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.