First thing I had to check was that this wasn't released on April 1st. But no, in a research paper titled "The Visual Microphone: Passive Recovery of Sound from Video" submitted for the upcoming SIGGRAPH 2014, a team of researchers have allegedly discovered how to extract sound from video images.
I'm still waiting for Snopes to debunk this, but this research collaboration from MIT's Computer Science and Artificial Intelligence Laboratory, Microsoft Research and Adobe Research makes the following claim:
When sound hits an object, it causes small vibrations of the object's surface. We show how, using only high-speed video of the object, we can extract those minute vibrations and partially recover the sound that produced them, allowing us to turn everyday objects--a glass of water, a potted plant, a box of tissues, or a bag of chips--into visual microphones.
Sounds crazy, no? Watch this and see (er, hear):
As you can see, the technology is predicated on using high-speed, high-resolution video. But just imagine if it was possible to apply this to old, audio-free archival footage.