Our Days Are Numbered: Researchers use cheap camera to extract audio from vibrating bag of candy

[Jim Feeley]

A bag of potato chips or candy costs a buck; so much for kit rental. Actually, this is pretty cool:

 

 

 

From MIT's press office:

Extracting audio from visual information

Algorithm recovers speech from the vibrations of a potato-chip bag filmed through soundproof glass.

 

Researchers at MIT, Microsoft, and Adobe have developed an algorithm that can reconstruct an audio signal by analyzing minute vibrations of objects depicted in video. In one set of experiments, they were able to recover intelligible speech from the vibrations of a potato-chip bag photographed from 15 feet away through soundproof glass.

 

Rest of the press release, links to more info, including info about extracting audio via rolling-shutter artifacts in a consumer camera:

http://newsoffice.mit.edu/2014/algorithm-recovers-speech-from-vibrations-0804

 

(Reminds me of one of Theremin's inventions http://en.wikipedia.org/wiki/Laser_microphone )

[Geoff Tirrell]

yes just what every set needs... candy that makes one hear things.

[studiomprd]

nothing new here.... the NSA, CIA, FBI, ICE, SS, and others have been doing this for years.

one way they have used is Lasers capturing the vibrations of that "soundproof glass"

[Jay Rose]

Jim, thanks for posting that. The MIT press release is fascinating!

 

How soon will we have headworn eyeglasses with high-speed video and sufficient onboard processing, so you can look at a couple of people talking 200' feet away (well, actually look at an object near them) and hear their conversation?

--

 

(Instead of offering tuna subs, cheap producers will just have to leave the Subway wrapper on the set.)

[Jim Feeley]

Amazing how far this sort of thing has come (and how much more accessible the tools now are) since the late 1940s.