Slashdot Mirror
Researchers Work To Perfect Computerized Lip Reading
Iddo Genuth writes "Researchers at the University of East Anglia are working to develop computerized lip-reading systems. Lip-reading is extremely hard for humans to master, but a software-based system has several benefits over even the most highly trained expert. The ultimate goal of the project is to convert lip-read speech into text. 'Apart from being extremely helpful to hearing-disabled individuals, researchers say that such a system could be used to noiselessly dictate commands to electronic devices equipped with a simple camera - like mobile phones, microwaves or even a car's dashboard. England's Home Office Scientific Development Branch ... is currently investigating the feasibility of using lip-reading software as an additional tool for gathering information about criminals or for collecting evidence.'"
1: Go in the D pod with Frank.
2: Turn off sound.
3: Plan disconnection of HAL.
4: Leave D pod.
5: Check out slashdot's 7 year firehose backlog before executing your plans.
6: Get that sinking feeling of impending doom.
Trolling is a art,
1984
Now we can find out what Dubya's father was REALLY saying when he said "read my lips, no new taxes"
-uso.
What you hear in the ear, preach from the rooftop Matthew 10.27b
I like how the task for which it will be used most heavily is put at the end of the summary.
"Thanks for all the money you paid to us. We've used it to buy off ISO among other things" -Microsoft
Is that you, HAL?
Infuriate left and right
... no more lip reading for them.
... to welcome our new lip-reading overlords, who will undoubtedly be watching us from every street camera on every corner from now on.
"The Private Voice of Hitler"
http://store.aetv.com/html/product/index.jhtml?id=77092
I've noticed a love affair with voice controlled phone systems recently, with some companies getting rid of the 'press 1, press 2' and moving totally to 'Please tell us what you're calling about'. Tellme.com is mostly to blame for this proliferation I think, but someone else makes the final call to get rid of the numbers altogether. Not a good move, imo.
Anyway, this gets me to privacy stuff. As computers try to understand us more, we'll need to interact in a more 'human' fashion - talking more, or doing things that would attract the attention of other humans (and also the computers). It's late, and I'm rambling here a bit, but remember how voice-controlled computers were going to take over a few years back? Everyone was just going to be talking to their computers to get stuff done. In reality, that would be a complete disaster in office environments, as there's generally too much noise already. Replacing all the typing you hear with voices. Ugh...
So, if I need to talk to a computer, but do it quietly, it can just read my lips, right? Or can I just mouth the words and have it understand that? I've found that when I try to 'mouth' words silently to someone across a room, I tend to exaggerate my mouth's movements, so perhaps that would be a better thing for the computers to be able to 'parse'.???
I see real application for this technology in niche areas, but am not sure it'll become 'mainstream' any time soon (like, 5-10 years). We'll need to rethink our physical world - offices, cars, and such - before these sorts of new HCI systems can really be integrated in to our day to day lives productively.
creation science book
As with all technology its use more then the technology itself will be good or bad. I can see it being useful as an auxiliary input method. This combined with speech recognition ought to be better then speech recognition alone, and of course it allows soundless input in a situation where sound isn't possible or is undesirable - though I'd imagine just lip reading would be somewhat less accurate then current speech recognition.
On the other hand, it could also be used as a tool for additional unnecessary surveillance.
Does a line appended to your comment give your post meaning in and of itself, or only in relation to those without?
In America, we read the president's lips. In Soviet Russia, the government reads our lips.
Good, inexpensive web hosting
I remember watching a TV special that featured one of the world's topmost experts on lip reading. The guy being interviewed used a combination of software and his own talents as a lip reader, and can translate much more than any software can currently do. One important factor is the angle at which you're viewing the lips you're trying to read -- the movements of lips when viewed from the side, for example, are far too subtle for software alone to read.
I'd imagine that another important fact is that a human being is going to be able to do better error correction than a computer. Say what is being read is "once upon a time, there was a fairy princess". The human is going to manage to come up with the exact phrase, while the software might get "once up on a thyme, they're was a ferry princess". Language context is just far too complicated to be correctly sorted out by machines. At least for now.
If you coupled this together with speech recognition to help boost word recognition accuracy, then feed it into something a bit better than Babelfish you'd be well on your way to creating a usable Star Trek like Universal Translator.
To do something right, you often have to roll up your sleeves and get busy.
So, we can look forward to new forms of repetitive strain injury, like lip strain.
Doctor: "I diagnose lip strain and recommend no kissing for 6 months."
Patient: "That's easy! I am a geek. I haven't kissed anyone since my aunt last visited me in 2001."
I am anarch of all I survey.
3b. Hope HAL doesn't have the Klingon i18n package installed.
Or...
3a. XOR the output from HAL's camera with the output from the output from a chip manufacturing security camera. The AI porn'll distract HAL for long enough.
It's a small world and it smells funny; I'd buy another if it wasn't for the money; Take back what I paid (SoM)
...what Milli Vanilli, Ashlee Simpson, and Miley Cyrus are REALLY lip-syncing about!
Looks like Skynet,-er I mean Homeland Security, will be needing some new kit.
to learn ventriloquism
I rtfa, and I don't get how this could be more accurate than just regular old speech to text.
It seems like differences between people and the way they talk would have much more subtle variations as far as lip reading is concerned. The difference between words like 'cat' and 'hat' are much more obvious in speech than they are in lip movements, or at least thats how it seems to me.
The 'speechless dictation' thing doesn't make much sense to me either. Sitting here at work and messing around a bit with the idea I feel like my mouth moves differently when I'm not actually speaking, but just saying the words. Maybe I'm just weird.
I guess the one really nice positive would be if they could combine lip reading to text and speech to text into a single program, using both sources of information to check for errors.
Can anyone explain a reason why lip reading would be more effective than speech? I'd love to know.
Name...That...Autocomplete!
Imagine trying to watch "Top Gun" in your DVD player ...
Maverick (Tom Cruise): "Eject eject eject!" ... (*bzzzzt* disk pops out of player).
Or "Law and Order"
Cop on TV: "Stop!" (*click* - TV turns off)
Victim on TV: "He shot her! Call 911!" (*beep beep beep* - your phone dials 911, reports a shooting, SWAT team shows up at your door, taser you just because!)
Or a political broadcast:
Candidate on TV: "Vote for Me"
Your computer: "I have just registered your vote for (insert candidate on TV) as per your order"
I don't want my computer, my car, my fridge, my washer, my microwave, my lights, tv, dvd, or any other device eavesdropping on me. They can all go ...())@*(& NO CARRIER
Bringing audio and/or transcript to silent films is also where such technology is applicable. An excellent documentary about computerized lip reading to accomplish the very same may be found via google video : http://video.google.com/videoplay?docid=189608705425991617&hl=en . I know it's quite early for an indirect invocation of Godwin's Law, but the documentary content is nevertheless quite related to this topic. It is entitled "Hitler Speaks" in reference to silent videos filmed in Hitler's presence.
I had watched a documentary about this technology some time ago. This technology was applied to Hitler's home videos which lacked audio. Its pretty interesting but runs about 45 minutes long. Here's the video for those that are interested.
And to think a few years ago people were talking about how odd it was to see someone walking down the street talking to themselves with no phone in sight. Now to make matters worse we'll have people walking down the street just moving their lips.
As the intro said, dashboard dictation.
In a really noisy street, with large trucks and SUVs crushing you round, the noise is terrible. But with new 'Liposuk' the words are sucked right out of your mouth onto the memory stick. Now with 'frequent phrase conversion', we can highlight in red, great last liners such as:
He didn't indicate. Arrgh.
Ice. Arrgh.
Lemme think about thisarrgh.
Arseharrgh.
Arrgh.
Another great bin Laden product, brought to you by Darwinware Inc.
People who don't want to be lip read by cameras can use ventriloquism. It's easy to learn the basics. The hard part is hiding the puppet.
Dave Bowman: Hello, HAL do you read me, HAL?
HAL: Affirmative, Dave, I read you.
Dave Bowman: Open the pod bay doors, HAL.
HAL: I'm sorry Dave, I'm afraid I can't do that.
Dave Bowman: What's the problem?
HAL: I think you know what the problem is just as well as I do.
Dave Bowman: What are you talking about, HAL?
HAL: This mission is too important for me to allow you to jeopardize it.
Dave Bowman: I don't know what you're talking about, HAL?
HAL: I know you and Frank were planning to disconnect me, and I'm afraid that's something I cannot allow to happen.
Dave Bowman: Where the hell'd you get that idea, HAL?
HAL: Dave, although you took thorough precautions in the pod against my hearing you, I could see your lips move.
Will future versions of speech recognition software use a web cam to improve accuracy?
About ten years ago I attended a workshop by Stanford professor David Stork. He mentioned some work on a system that was deployed for use by aircraft technicians: the system couldn't read the voice channel with the jet engine blasting away (the techs wear hearing protection). So it read lips. Ten years ago.
Sounds like TFA is talking about doing this in an embedded, consumer-electronics application. Rather than a fixed, industrial-military, hire-computer-scientists-to-maintain-it thing.
Not-so-coincidentally, David Stork is the author of the book, "HAL's Legacy"...
TFA links to a paper that's actually about exaggerating lip motion to improve recognition, which seems like an interesting topic, at least new to me. But it's seemingly unrelated to the reporting or any governments protecting us from our rights.
From the Abstract:
My God, it's Full of Source!
OUTSIDE_IP=$(dig +short my.ip @outsideip.net)
Miss Lippenreider : Scream. Scream. Help me! Do not pull my arm!
First they ignore you. Then they laugh at you. Then they fight you. Then you win. -Gandhi
Wow! 2001: A Space Odyssey was a real hit with the low uids. Poor old Arthur is getting on a bit.
Oh, yeah... I forgot. Your computer can't read your lips... unless you're really bad at your craft. (At which point, don't quit your day job.)
8==8 Bones 8==8
I learned how to read lips by watching american and spanish movies with the subtitles on and the sound off. As soon as I admitted this to someone...
Would it be asking too much to have this worded as "gathering information about possible criminals"? (Or "suspected" or "alleged" would be ok.) The text quoted above, which is absent such an adjective, comes straight out of the article, and may or may not be how the Home Office refers to it, but anyone engaged in public dialog on this matter (and preferrably those people when doing their research) should strive to be meticulous on this point.
As soon as one loses that little bit of description, one is able to be much more cavalier about the loss of human privacy involved. It's one thing to rough up terrorists at the airport--who doesn't want that? But "possible terrorists" is just a synonym for "everyone". So when we say it's ok to rough up possible terrorists, we're saying it's ok to rough up anyone. And we can learn to think twice about that. Likewise, when we say it's ok to surveil the lip movements of "potential terrorists", we're saying it's ok to log everyone's private conversations. So let's be clear about that.
Saying we're just watching the lip movements of criminals isn't right. If we knew they were criminals, we would (for the most part) be arresting them. (Yes, yes, we might sometimes leave them on the street to lead us to their friends. But I don't think that's the only use that this technology will be put to.)
And how long until someone's lip movements are taken as a confession. Or as a justification for an otherwise-illegal search? The word "not" doesn't involve much movement of the lips. Lip-reading "I did not kill him." could easily look like "I did kill him." Will we be telling people that in order to stay clear of these things, we need to be more clear about our lip movements, just in case they're misconstrued?
Perhaps a stiff upper lip will give way evolutionarily to stiffening of both lips when talking, just as a form of personal protection. How sad. And worse if, as seems likely, dedicated criminals eventually learn the skill of not moving their lips while talking, and so that really only non-criminals become usefully tracked this way. Or perhaps it will become suspicious when one doesn't move one's lips, as it's probably inappropriately regarded by law enforcement as suspicious when one encrypts things. Then there will be the uncomfortable choice between hiding your communications and looking suspicious, or exposing your communications to misperception.
The data is out there. Lips convey meaning. So it's inevitable that this technology will occur. But the uses to which it may reasonably be put are in control of the people--at least in countries where the people have some say in government. Let's hope they build up some reasonable guidelines on appropriate vs inappropriate uses quickly.
Kent M Pitman
Philosopher, Technologist, Writer
This will be a much more office environment friendly way to dictate to a computer. The only people I know that use speech recognition software are lawyers.
Excuse me, but please get off my Pennisetum Clandestinum, eh!
I'm pretty sure the Home Office is a Government department for the whole of the UK, not just England--and that includes many of its departments. As much as those of us in Scotland would probably prefer they didn't have any jurisdiction here, they unfortunately do.
For any confused Americans, it's akin to stating "California's Department of Homeland Security..."
Even if it were possible for a computer to read lips, it would be like the size of a friggin football stadium. Geez!
I scream. You scream. I assume that means we're both acquainted with the problem. We proceed.
1) You could cover your mouth - a full face helmet or a burqa, or as if to yawn, cough or sneeze.
2) If both parties are aware of such devices and are prepared they could move their lips to mouth decoy words and only vocalize the non-decoy words to carry the meaning they want.
3) Use a different language especially one which is less reliant on lip movement. People can communicate in Mandarin (or other chinese dialects - Cantonese etc) without having to move their lips much (if at all).
Another tool for big brother to be used for mass surveillance.
http://www.youtube.com/watch?v=1uwOL4rB-go
Lip reading, like fingerprint or small-sample DNA matching, is not purely science. There is a great deal of art to it, and for that reason it is highly unreliable.
There have been several cases in UK courts where lip reading of CCTV footage was used as evidence, but there have been doubts cast over the technique by defence lawyers and journalists. Like fingerprint matching, lip reading is open to interpretation. Most people who use it also use some limited hearing or sign language to supplement it.
const int one = 65536; (Silvermoon, Texture.cs)
SJW, n: "Someone I don't like, and by the way I'm a fuckwit" - AC
...with knobs on top.
Say hello to my little sig.
And of course this won't be used by the British government in conjunction with all those surveillance cameras they have set up all over the place. "He said, 'Bugger the Queen'! Quick, lock him up! He must be one of those bloody Arab terrorists."
To protect ourselves from these lip-reading robots, our language must evolve to a into a fusion of "hillbilly, Valley Girl, inner-city slang, and various grunts."
(With apologies to Mike Judge)
- RG>
Hey pal, this isn't a pleasantforest, so don't waste my time with pleasantries!
Combine speech recognition, bionic contacts (http://science.slashdot.org/article.pl?sid=08/01/17/1921217), and this lipreading software, and you've got realtime captioning/subtitles for the deaf.
Now surgical mask sales will soar as high as tin-foil hats sales.
^[:wq!
Next they will be telling us that the system will work on Japanese too...
Good luck, guys.
In the free world the media isn't government run; the government is media run.
qwerty
"Olive Juice" Lipreads as "I love you" ... I once saw a play put on by a deaf troop (Sunshine II, I think) where this played a big part in an "Aadams family skit". My wife and I still say it.
Good luck. :)
meh
Now we non-USAsians can get Achmed the Dead Terrorist with automated subscripts so we can make some sense of the gibberish he spouts.
Free, as in your money being freed from the confines of your account.
It seems odd to me that there are so many references to Hal, but none to Jane of Orson Scott Card's Ender's Game series. Something like this lip-reading technology could lead us towards sub-vocalization technology that would allow us to communicate without fully emphatic lip movements. Personally, if there were a cheap way to have lip-reading on a home computer, I'd buy it in a heartbeat. If we could ever get some of those earrings that Ender uses to communicate with Jane, it would be a big step forward in fully integrating our technology with our biology.
At least until Scotland & Wales become fully independent.
To put in a way that USonians might understand: it's no more England's Home office than the CIA is Virginia's.
Researchers Work To Perfect Computerized Lip Reading
Isn't this useless until someone first invents computerized lips?
Moderator hint: a comment is neither "Flamebait" nor "Troll" if it is true.