Novel technique to extract audio from video feed

New York: Scientists have devised a simple optical technique to recover spoken words from just a video recording of objects in the room.

The method uses an image-matching process based on vibration from sound waves.

"The technique may find applications such as the passive detection of conversations inside of a building from a far distance," said one of the study authors Zhaoyang Wang from the Catholic University of America in the US.

"The paper shows that the sound creates minute vibrations in objects and that these vibrations - given the right equipment - can be picked up from a video signal," said Reiner Eschbach, associate editor of the journal Optical Engineering that published the paper.

The technique is based on the fact that sound waves are mechanical waves that cause air to vibrate when travelling.

That vibration through air can cause vibration of objects located in its travelling path, especially if the objects are lightweight, thin and flexible such as a piece of paper.

The vibrations, although usually with small amplitudes, can be detected and analysed algorithmically and audio reconstructed based on those calculations.

The study appeared in the journal Optical Engineering.