For a while I was toying with their audio matching algorithms to see if I’d get caught. I turned audio into a binary image bmp, found the euclidean center of the “sound waves”, turned it back into a “sound wave” and uploaded to see which systems caught it and which didn’t. I was impressed that they found them which tells me that an automated version of the method I experimented with (euclidean centers so what you’re left with is pure tones) – is part of the “fingerprint” they use to identify copyrighted audio.

For a while I was toying with their audio matching algorithms to see if I’d get caught.
I turned audio into a binary image bmp, found the euclidean center of the “sound waves”, turned it back into a “sound wave” and uploaded to see which systems caught it and which didn’t.
I was impressed that they found them which tells me that an automated version of the method I experimented with (euclidean centers so what you’re left with is pure tones) – is part of the “fingerprint” they use to identify copyrighted audio.

Leave a comment

Your email address will not be published. Required fields are marked *


9 × = thirty six

Leave a Reply