The sound of silence: an end to noisy communications

Mar 02, 2010
Two people talk on mobile phones in Central business district of Hong Kong, 2002. A new technology unveiled at the CeBIT fair transforms lip movements into a computer-generated voice for the listener at the other end of the phone.

It has happened to almost everyone. You are sitting on a train or a bus and someone right next to you is annoyingly shouting into his or her mobile phone.

But those days could soon be past with "silent sounds", a new technology unveiled at the fair on Tuesday that transforms lip movements into a computer-generated voice for the listener at the other end of the phone.

The device, developed by the Karlsruhe Institute of Technology (KIT), uses electromyography, monitoring tiny muscular movements that occur when we speak and converting them into electrical pulses that can then be turned into speech, without a sound uttered.

"We currently use electrodes which are glued to the skin. In the future, such electrodes might for example by incorporated into cellphones," said Michael Wand, from the KIT.

The technology opens up a host of applications, from helping people who have lost their voice due to illness or accident to telling a trusted friend your PIN number over the phone without anyone eavesdropping -- assuming no lip-readers are around.

The technology can also turn you into an instant polyglot. Because the electrical pulses are universal, they can be immediately transformed into the of the user's choice.

"Native speakers can silently utter a sentence in their language, and the receivers hear the translated sentence in their language. It appears as if the produced speech in a foreign language," said Wand.

The translation technology works for languages like English, French and Gernan, but for languages like Chinese, where different tones can hold many different meanings, poses a problem, he added.

Noisy people in your office? Not any more. "We are also working on technology to be used in an office environment," the KIT scientist told AFP.

The engineers have got the device working to 99 percent efficiency, so the mechanical voice at the other end of the phone gets one word in 100 wrong, explained Wand.

"But we're working to overcome the remaining technical difficulties. In five, maybe ten years, this will be useable, everyday technology," he said.

Explore further: Team shows calibrated multiple-projector spherical display

add to favorites email to friend print save as pdf

Related Stories

Google developing a translator for smartphones

Feb 09, 2010

(PhysOrg.com) -- Google is developing a translator for its Android smartphones that aims to almost instantly translate from one spoken language to another during phone calls.

IBM Technology Improves English Speaking Skills

Oct 26, 2006

Researchers at IBM's India Research Laboratory today announced that they have developed a Web-based, interactive language technology to help people who speak English as a second language improve their speaking skills.

Recommended for you

Engineering the Kelpies

8 minutes ago

Recently, Falkirk in Scotland saw the opening of the Kelpies, two thirty metre high horse head sculptures either side of a lock in a new canal extension.

Technology on the catwalk

18 minutes ago

Summer days bring thoughts of beach picnics, outdoor barbecues and pool parties. Yet it only takes the buzz of one tiny mosquito to dampen the fun.

Godzilla stomps back in ultra HD, wires intact

51 minutes ago

At a humble Tokyo laboratory, Godzilla, including the 1954 black-and-white original, is stomping back with a digital makeover that delivers four times the image quality of high definition.

Dismantling ships and the trajectory of steel

53 minutes ago

Tell me how you dismantle a ship, and I'll tell how a region can prosper from its steel! This could be the motto of this master's cycle at ENAC during which the projects of two civil engineering students ...

Hackerspaces used to turn ideas turn into reality

3 hours ago

At HeatSync Labs, the tables are littered with computer chips, pens, pads and tools while the room is abuzz with the chatter of would-be inventors hoping to change the world—or just make cool things. They are part of a ...

User comments : 3

Adjust slider to filter visible comments by rank

Display comments: newest first

MorituriMax
5 / 5 (1) Mar 02, 2010
Oh please, computer language translation has been piss poor since they started working on it for the simple fact that it is very very hard for a computer to understand exactly what someone is saying and what they MEAN based on the context of the sentence they are currently uttering.

Do they expect us to believe they have solved this massive problem because electrodes can tell what miniscule impulses reported by the phone sensors really does mean?

I mean, its hard enough to understand what they are SAYING, much less translate that somehow from one language to another completely different language accurately. Look at Google Voice. The people actually TALK and even with that major hurdle solved (muscle movements to actual audio content) they still get very hilarious results on what is transcribed in THE SAME LANGUAGE.
maxcypher
not rated yet Mar 02, 2010
I was a bicycle messenger in San Francisco back in '89 when I first saw someone in a business suit talking to herself out loud while striding up Market St. I suddenly realized that the only reason I didn't think she was just another crazy was because of the suit she wore.

Well, now it seems -- if the computer language problem gets solved -- we'll be seeing people walk down the street while talking silently to themselves.

Oh wait... We already do that.

MorituriMax -- Klaus Kinski fan?
jgelt
not rated yet Mar 03, 2010
This is interesting, the idea of using vocalization muscles of phonemes instead of fingers for letters.
It reminds me of the beautiful korean written language that depicted the buccal configuration required for the sound of the letter- so intuitive anyone could read in a few hours. Not that I regret being the only guy in a typing class back in the day.