HackerTube
HomeLongsLikedHistoryWatch laterCategoriesPlaylistsSettings

The Visual Microphone: Passive Recovery of Sound from Video

Abe Davis's Research1 HN recommender · recommended in 1 month, 2015-2026
YouTube
1.9M views · 12 years ago · demo · evergreen

MIT researchers show that sound can be recovered from silent video by analyzing tiny vibrations in objects such as a potato chip bag. It works even with consumer cameras by using rolling shutter.

HN commenters cite it as the classic demonstration of audio recovery from video in surveillance and privacy discussions.

Information theory & signal processingComputer vision, speech & NLPPrivacy, surveillance & cybercrime#audiofromvideo#mitcsail#surveillance#vibrations#signalprocessing

6 comments from Hacker News

@spyder2026 · in “WiFi Could Become an Invisible Mass Surveillance System”

with a high speed camera any vibrating reflective object like a potato chips bag can become a microphone: ▶ this video

CitesView on HN
@bbbobbb2020 · in “Spies can eavesdrop by watching a light bulb's vibrations”

Here similar experiment, 6 years ago: ▶ this video If you think that actual government agency cannot do even more easily with better equipment in 2020 you're kidding yourself.

CitesView on HN
@ehsankia2018 · in “Show HN: Lipreading with Deep Learning”

You can do it with video too, even: ▶ this video Also, this is only tangentially related, but you can also see through walls using WiFi: link

CitesView on HN
@anfractuosity2018 · in “If you watch closely enough, everything is a speaker”

See this - ▶ this video They show audio captured from a 60fps video from a DSLR exploiting the rolling shutter. I'm not sure if you can use less than 60fps though?

CitesView on HN
@eesmith2017 · in “Prostitution cases dismissed because cops’ cameras mistakenly recorded audio”

"security cameras outside of stores" would be in public areas, yes? The Lifehacker link you pointed to says "Generally speaking, you have the right to record video in all public spaces without need of consent." Now for the fun part - it can be possible to extract audio from video, by careful processing of the small motions the sound induced in objects in the frame. See ▶ this video . High-speed camera is best, but at the end they show how a regular consumer-level camera can also be used.

RecommendsView on HN
@lawry2015 · in “Periscope by Twitter”

Remember even if you mute your microphone, it's still possible to extract audio from the video you are streaming: ▶ this video

CitesView on HN
This AI actually WORKS!!! - NVIDIA RTX Voice7:47

This AI actually WORKS!!! - NVIDIA RTX Voice

ShortCircuit
1.8M views • 6 years ago
Visualizing video at the speed of light — one trillion frames per second2:47

Visualizing video at the speed of light — one trillion frames per second

Massachusetts Institute of Technology (MIT)
12M views • 14 years ago
Reveal Invisible Motion With This Clever Video Trick14:20

Reveal Invisible Motion With This Clever Video Trick

Steve Mould
2.8M views • 6 years ago
D/A and A/D | Digital Show and Tell (Monty Montgomery @ xiph.org)23:53

D/A and A/D | Digital Show and Tell (Monty Montgomery @ xiph.org)

FL Studio
647K views • 13 years ago
The Eleventh HOPE (2016): Coding by Voice with Open Source Speech Recognition46:20

The Eleventh HOPE (2016): Coding by Voice with Open Source Speech Recognition

Channel2600
13K views • 9 years ago
Movie reconstruction from human brain activity0:29

Movie reconstruction from human brain activity

Jack Gallant
6.7M views • 15 years ago
Floyd Toole - Sound reproduction – art and science/opinions and facts1:13:57

Floyd Toole - Sound reproduction – art and science/opinions and facts

CIRMMT
144K views • 11 years ago
Larynx Demo54:13:03

Larynx Demo

synesthesiam
14K views • 5 years ago
Hold music used to sound better. Here's why.3:36

Hold music used to sound better. Here's why.

Tom Scott
2.9M views • 8 years ago
Imaging at a trillion frames per second | Ramesh Raskar11:02

Imaging at a trillion frames per second | Ramesh Raskar

TED
3.2M views • 14 years ago
Trackers: The Sound of 16-Bit41:12

Trackers: The Sound of 16-Bit

Ahoy
2.1M views • 4 years ago
I Saved a PNG Image To A Bird30:53

I Saved a PNG Image To A Bird

Benn Jordan
2.1M views • 1 year ago
Dial Up Modem Handshake Sound - Spectrogram0:29

Dial Up Modem Handshake Sound - Spectrogram

Bitcore
3.6M views • 13 years ago
VIDEO ROOM 1000 COMPLETE MIX -- All 1000 videos seen in sequential order!2:51

VIDEO ROOM 1000 COMPLETE MIX -- All 1000 videos seen in sequential order!

ontologist
2.4M views • 16 years ago
Speech Recognition Breakthrough for the Spoken, Translated Word9:05

Speech Recognition Breakthrough for the Spoken, Translated Word

Microsoft Research
1M views • 14 years ago
CVPR 2018: Learning to See in the Dark3:31

CVPR 2018: Learning to See in the Dark

Chen Chen
190K views • 8 years ago
AI Learns Noise Filtering For Photorealistic Videos | Two Minute Papers #2154:17

AI Learns Noise Filtering For Photorealistic Videos | Two Minute Papers #215

Two Minute Papers
65K views • 8 years ago
Speaking Piano - Now with (somewhat decent) captions!2:41

Speaking Piano - Now with (somewhat decent) captions!

TheMcphearson
2.2M views • 17 years ago
Adobe MAX 2011 - Photoshop Image Deblurring sneak6:26

Adobe MAX 2011 - Photoshop Image Deblurring sneak

Peter Elst
1.8M views • 15 years ago
Eulerian Video Magnification4:28

Eulerian Video Magnification

Miki Rubinstein
788K views • 14 years ago