News for hackers. Stuff that matters.
Re:The Technology Behind Making the Internet Archive into th... by tim333 on Thursday May 12, 2016 @04:29PM (#11686524)
tl;dr they are archiving political ads off TV and try recognising them in software by their sound using http://labrosa.ee.columbia.edu/matlab/audfprint/ I think.

They don't say how political ads sound different from other TV - I guess it works? Or maybe they are just using it to check if they have that ad already like how Shazam works?

Re:The Technology Behind Making the Internet Archive into th... by slifty on Thursday May 12, 2016 @04:34PM (#11686567)
It's all about the FREQUENCIES! Actually though, this system can be used to find copies of any sound -- sound bytes, commercials, music, whatever. We just happen to be using it for politics because we apparently hate fun.

We're using the python port of audfprint though: https://github.com/dpwe/audfprint

And yes -- we have a big bucket of known ads, and a big bucket of archived programming, and we're comparing new content with the appropriate buckets.

NOTE: we are talking about ways to release the fingerprints of all the TV we archive so anybody can "search" TV for copies of sounds.

Re:The Technology Behind Making the Internet Archive into th... by danso on Thursday May 12, 2016 @05:01PM (#11686758)
There are possibly some obvious and unique heuristics. For example, the FEC requires that broadcast commercials must either an explicit audio statement of who authorized the commercial:

http://www.fec.gov/pages/brochures/notices.shtml#appearance

e.g.

"I'm Ted Cruz and I approve this message"

"This message paid for by the Americans for A Better Tomorrow Tomorrow"

There are very, very few non-political commercials that have this kind of phrasing.

edit: I'm only referring to how political commercials are different from non-political commercials. Obviously, the above heuristic has not much value in determining whether a particular ad is the same one as one already recorded and identified by the Archive.