Extracting audio from visual information

Post by PeterisP » Sat, Aug 09, 2014, 7:02 AM UTC

RaphiePS wrote: post #94

radarsat1 wrote: post #74

Earlier quoted context omitted.

You missed the part where 60 frames per second only allowed to identify the speaker and the number of people in the room. > Because of a quirk in the design of most cameras’ sensors, the researchers were able to infer information about high-frequency vibrations even from video recorded at a standard 60 frames per second. While this audio reconstruction wasn’t as faithful as it was with the high-speed camera, it may s…

If you watch the video in the post, the demo is surprisingly accurate.

Post by Houshalter » Sun, Aug 10, 2014, 5:21 AM UTC

PeterisP wrote: post #132

Houshalter wrote: post #97

How much vibration does sound actually cause an object. I tried humming near various objects and noticed nothing. I used to be really interested in early mechanical microphones and sound recording, but I couldn't find much information on how they work either.

Your eyes wouldn't be able to see a 2000 Hz vibration, most vibrations that we perceive as sounds (except from the very low vibrations) are so fast that even with a huge amplitude they'd be just a motion blur for our eyes. Now, a 2000 fps camera can see things that a naked eye can not.