Slashdot Mirror
Neural Net Outperfoms Human in Speech Recognition
orac2 writes "Here's a press release (with a real video clip) on a neural net that can recognise speech better than humans - even in noisy environments. The network uses just 11 neurons. They did it by incorporating an aspect of biological neural networks normally ignored by artificial networks; the timing of signals between neurons. Beyond the immediate application to speech recognition the wider implications for all neural networks are obvious. " Neurons. Mmm.
We still have a full year in which to make a fully functional HAL-9000. Based on his neurosis, I imagine he must be a Neuron computer. So let's get cracking! All we need are a few million neurons, some clear plastic holographic hard drives, and infrared fish cameras. Then train, train, train! It would be a rare first for technology to achieve the level of sci-fi by the time sci-fi predicts it will exist.
XeoMage
Of course everyone's a pessimist, this is /. it's a required trait--either that or a cynic
;)
Cheers
Tape surveillance and a human filter can only go so far. Parabolic antennae are bulky and easily recognized. Humans using digital filters require training and equipment booking, which could be expensive depending on the amount of noise in the recording and the expertise of the user.
These speech recognition devices could put surveillance within reach of anyone, regardless of their expertise, without hiring potentially expensive human filters. You or I, without any surveillance experience or knowledge of digital filtering technology, could trail certain people and tape their conversations even in crowded areas.
ian
How does this new technique affect the amount of time it takes for a network to learn?
Actually, it looks as though this thing doesn't understand language better than humans (if at all). All it can do is pick out the sounds and form them into words. It still does not know what the words mean.
In essence, what was created is little more than a super-hearing-aid. Certainly a good thing for the hard-of-hearing (and this one, it would seem, could significantly boost the hearing of anyone, even those with "normal" hearing to start).
Fred Loki Qwertyfaster
Actually, I suspect this is rather closely related to how the human brain works in some cases, but perhaps more efficient due to some shortcuts we can take. How could consciousness work without some form of broadcast? Somehow, thoughts are being moved around so different parts all over your brain are hearing the same things.
There is some very definite predefined structure to the brain between the gross and cellular anatomy. It isn't just a raw neural net that is trained by physical pleasure and pain. Somehow, consciousness, intent, recognition of success and failure are built in at the highest level and recognition of the same sound in different pitches and visual recognition independent of image location on the retina are built in at a low level.
I suspect if you could read and analyse all of the connections, it wouldn't look like one big mess of seemingly random connections, but a lot of small neural nets arranged and interconnected in hierarchies, sorting pipes, buses, and the like (which aren't especially neural mechanisms, they're probably better done in the familiar ways we've developed that suit silicon).
I agree about using more neural nets on the problem. I never meant to imply that it would be anything more than a single component in a larger system. At some point in the process, you need to recognize sounds, whatever you do with them later.
What I dislike is the way some people treat neural nets as a magic bullet, as if we only need to make a big enough neural net and it will solve any problem. I think only small neural nets really work well; beyond a few dozen neurons, an external structure is needed to get anything to work.
(IMHO, the most important thing for *-recognition programs to start doing is admitting that they didn't understand and asking for clarification; "best guess" is not a good strategy)
Unfortunately, no one can be told what the Matrix is, you have to see if for yourself.
(now available on DVD at a store near you!)
And how many still believe that Echelon is not capable of recognizing words in conversations automatically?
-
Pulling out 1 word out of 4 possibles is NOT hard, when you know those are the only possibilities. So what USC have achieved is NOT impressive.
Dragon was pulling the word out from 60,000 possibles. That is FAR harder, and MUCH more impressive.
Moderators, get a clue.
A bitchin' Beowulf cluster of Alphas (with Dvorak keyboards) would romp ass over any friggin' "neural net"...
Who's faster?
* John C. Dvorak
* Qwerty Berst
This breakthrough is a complete disaster for Intel -- they have been struggling to find a valid reason for people to upgrade to Pentium IIIs. Witness the absurd marketing attempt to convince people that they need Pentium IIIs and Intel's WebOutfitter service to really enjoy the Internet -- when all it really takes is a computer with a decent graphics card and reasonable Internet connection. Video decompression and game playing are tasks which a Pentium III can legitimately improve -- but only a limited subset of the population cares about those tasks. The real "killer app" was speech recognition -- which until today appeared to require tremendous amounts of processing power. Speech recognition is something virtually everyone could use -- and these two guys have just disproven the assumption that vast processing power is required. Monir
That's an awful lot of bitterness for what amounts to a signal processing technique. Besides, last I heard there were quite a few successful applications for neural networks - credit card application processing and financial analysis, to name two.
wants to be the first monkey to touch the monolith
No, it's just preachy BS.
It's obvious you are just tripping. The creator of the first one that says "I'm Sorry Dave" will think he is Dave, or that he has been mistaken for someone who IS Dave.
As far as "glorifying themselfs" for mimicking what they already saw with the human brain, WTF are you talking about? Of course they're proud of themselves! They did something with a computer that nobody had ever been able to do before. That right there is fucking cool! I'm proud of them too, and I go to UCLA! (the researchers in question were from USC, in case anybody missed that)
--Mizerai
There is more than just a little Big Brother possibility to this. If this technology actually works as advertised, it eliminates the last technical barrier preventing governments from monitoring all voice communications all the time. Heretofore, this was not practically possible because of the manpower required to listen to millions of voice calls; this technology will make it possible to search for key phrases in real time as well as to archive millions of calls efficiently. The fact that it is apparently both cheap and simple only makes things worse.
Almost equally disturbing is the apparent ability of the Berger-Liaw system to distinguish individual voices from background noise, which raises the specter of governments being able to use almost unimaginably faint sounds to avoid more intrusive methods of bugging, and the monitoring of conversations in crowds. Combine that with existing off-the-shelf technology for face recognition...
Let's just say that I will be very surprised if the first customers for this technology aren't in Beijing and even more surprised if they aren't quickly followed by the dolts in Washington.
And hey, if I can reconstruct what you say inside your home from the weak sound waves that drift out into the street, that might not even require a warrant...
Proud member of the Weirdo-American community.
The net has to know what it is listening for inside of the noise before it can actually pick it out.
NO, IT DOES NOT!!
It all comes down to statistics. Speech is a non-white signal. Noise is white. If you have two microphones/ears, you simply search for the linear combination of the two signals that is the most un-correlated temporally, and voala! You have found the speech signal. This is known as blind separation.
It's difficult to evaluate this system given the sparse amount of information available. I, for one, am incredibly skeptical at this point.
e al/real_video.html
a) There is no statement of the train/test procedure for the neural net. It's fairly easy to get good performance if you're training your system on the same dataset that you test. Without this information, you cannot make a reasonable judgement.
b) If you listen to the audio samples in the video at
http://www.usc.edu/ext-relations/news_service/r
You can notice a significant difference in the times of the samples (e.g. "stop" is shorter than "yes"). A fairly unsophisticated NN can pick up on the length of a sound sample and generalize from there. I didn't hear any statement saying that in the official training and testing all sound samples were of the same length.
It's really a mess. If someone has a journal article or other piece of reliable information on this research, a pointer would be appreciated. Until then, I'll be feeding Clever Hans.
From watching the realmedia thing, it seems like the sounds sample it gave for recognizing the four words in random order with noise played a word, then silence, then word, etc.
Couldn't the system simply be detecting the length of the signal and interpreting it that way? With so few sample words it seems hard to tell how the thing is really working -- something which is not really explained.
Maybe I'm just way off tho.
This is my feeling, too. This might be just the tip of the iceberg.
Can anyone see how something like this could be made using software?
Kythe
(Remove "x"'s from
Kythe
I'm more concerned that USC is trying to patent the "system and the architectural concepts on which it is based". As a computational biologist who uses neural nets in my work, I rely on the AI community to develop the underlying algorithms. If they get a patent on the algorithm and not just their hardware, that would severely limit the use of this breakthrough in other scientific areas.
JMC
Doesn't the English languages use only a few dozen sounds ("phonems" or something)?
Once you can recognize those sounds I'm pretty sure it's easy convert a list of those sounds to a written sentence. I'd bet it could be done in under 200 lines of Perl. :)
But I'm no speech recognition expert.
but not this well.
From what I remember from my NN class, there have been spike train networks for at least a decade. They're mostly relegated to the backs of the NN books, though.
I'm pretty skeptical about this as being a major breakthrough until I see an algorithm or code. It looks promising though & demonstrates that these networks deserve more research.
A 4004 could do that, just takes a week :)
All it did was match her voice recording of her saying his name as key to a database against her saying his name. Sheesh, hype hype hype hype hype hype.
The message on the other side of this sig is false.
It said they'll apply for a patent - I wonder how much the patent will cover. I really hope they don't manage to get a patent covering the use of temporal information in neural networks as a whole - ordinarily, I'd assume they wouldn't, but given some recent patents, I tend to worry.
-=Best Viewed Using [INLINE]=-
I believe that the point was that this could potentially make wiretapping and so forth cheaper by several orders of magnitude. And simple economics suggests that when something gets that much cheaper, people may use it more. So the real fear is that if it's that easy/cheap, then the government will be able to use it in far more situations.
I think many people are missing the point.
Ok, ya, this thing can do voice regognition. But the advantage of that is not so that I can dictate this speach instead of typing it (although I would) the advantage is "changing the different user interface".
Right now, computers are very specific in their instrution taking. Click a little to the left of a button, and the computer has no idea of what you are doing. Type copy instead of cp into most unix's and it won't even copy the dumb file.
If this neural net can distinguish my voice from others in a room, I can talk to it. "Computer, check all TV channels for the baseball scores and display on this screen please."
Not only does this make the computer easier to use, and more usable for more poeple, it makes it more useful. ***If frees us from sitting at a workstation.*** Notice in Star Trek they can say, "Computer, what is the population of Earth?" and it will respond.
Granted, Artificial Intelligence must be improved to allow the computer to understand this instruction, but the voice communication is ESSENTIAL.
I look forward to the days when I can chat with my computer.
I wonder what a neural net made of bogons, morons and vogons would be like?
----------
In a real emergency, we would have all fled in terror, and you would not have been notified.
I can see this capability being put to great use, because of all the places where there can be noise, and having a computer with speech recognition abilities like this would be very helpful as they could automate more things by speaking to the computer.. each person having their voice recognized by the computer (and, just for insurance, having at least dual processors, if not a few more), and each person yapping their commands to the computer and getting instant results...
Imagine calling your computer up with a phone.. any phone, a pay phone, etc.. and getting it booted up and ready for you.. how convenient!
Insert mind here.
I know speech recognition seems cool and it will be very good for the disabled, but it's not a purely good thing.
Now, instead of requiring at least 2 people to invade your privacy and listen to everything you say, one supercomputer and a bunch of listening devices let The Man (tm) listen to thousands of people at once and scan the transcripts for keywords and sentances.
Actually, I used to (still do, I guess) know someone at Bell Atlantic (formerly Nynex) who was involved in developing their voice recognition stuff. However it was all server-side, and the hardware-vendor they used was pretty unreliable, IIRC. General Magic has been working on this type of stuff too, c.f. Portico, myTalk, etc. Again, limited word choice, but ability to distinguish words in noisy environments. Has anybody thought of using this to improve acoustic couplers? The main problem is background noise, right? And only two "words"... --Josh 0schrier_j@spcvxa.spc.edu/schrier@qtp.ufl.edu
I get the impression that this net did not perform better "even" under noisy conditions, but "only" under noisy conditions.
r ies/36013.html
Here's the original link
http://ww w.usc.edu/ext-relations/news_service/releases/sto
If I'm right about that, then this development (while still insanely cool - don't get me wrong) might not be so surprising. As I recall from college brain-and-mind psych courses, humans use a variety of factors when singling out a lone voice or conversation in a noisy environment. These include spacial orientation, visual cues, etc. My prof called the "cocktail party effect". Rob them of these cues, and it isn't suprising that they are hobbled.
Also, computers have the mixed blessing of ignoring information patterns unless they are instructed to do otherwise. A person, listening to white noise, would subconsciously attempt to find meaning in every bleep and scratch. A computer, listening only for certain cues, can disregard the majority of the signal.
I would be interested in learning what rate of word recognition this system achieves. Current technology manages about 90%, which means one in every ten words is heard incorrectly. If they could improve that to 99.9% or even just 99%, we might actually get some speech-processors in Office desktop products.
-konstant
-konstant
Yes! We are all individuals! I'm not!
I've not yet seen anybody comment on the ultimate use of this technology. Just imagine, we could finally know what the lyrics in Louis Louis are. AC
I guess I won't be able to safely mutter insults about my manager under my breath any more ...
> These guys should publish something when they get half that good on any axis.
Agreed. This whole thing smacks of yet another PR department, in yet another large research organization releasing something they dimly comprehend but know how to hype to the max, simply because that's what they get paid to do. (It makes justifying enlarging the staff of the PR department so much easier because just look how busy they are...)
Want to bet that the researchers didn't write (or even edit much of) the press release? Want to bet that their scientific publications on the topic do not make anything resembling such grandiose claims? Want to bet that they are severely embarassed by at least one aspect of this press release?
Or is it just that they have spun off a new company (majority owned by USC undoubtedly) that will be IPOing in the near future?
(Me? Cynical?)
...is the number of conspiracy theorists that are going to come out of the woodwork shouting about how it will allow the government to spy on us more effectively.
Didn't it take over 300 to reproduce the behavior of a ringworm recently?
I wonder how long before we see silicon for a net like this... or Sony incorporates it in the next Aibo...
Napster-to-go says "Fill and refill your compatible MP3 player", which is a lie. It's not MP3. It's WMA with DRM.
Time to open you wallet dude!. html
Check out this link:
http://www.hp.com/jornada/products/430se/overview
The only reason all cover-ups appear to fail is that you never hear about the ones that succeed.
The scariest thing about all this is that it kind of gives us an entry into artifial intelligence that we have never seen before, not this big, not with such an impact. This actually proves that a machine can do things better than man, but now it proves that even the language we speak, it can understand better than even us. This opens doors to all those government conspiracies about bugging devices and such.
My wife's constantly complaining that I don't listen whereas I think the problem's increasingly that I don't hear well; I'm over 35 and have been putting off going to audiological screening for awhile now. This article makes me wonder: Will we eventually see hearing aids that specialize in recognizing and resynthesizing speech? (In case you care, what triggered my pondering was the mention that this works well even in noisy environments, and in any kind of background noise at all, I'm having real trouble understanding speech lately.)
"How many light bulbs does it take to change a person?" --BMcC-->
I can see it now.. If you're in a loud noisy place (like a rock concert), you can make a cell phone call to someone and the new speech recognition software would be able to translate the call.
I can just image such a call now...
"Yes! No! Fire! Stop! No! Fire! Yes!"
Of course, you'll need to have only 11 neurons to understand the conversation.
htt p://www.usc.edu/ext-relations/news_service/release s/art/berger_liaw360x246.jpg
:-)
Looking closer at this pic and zooming in a bit.. I'm noticing something..
11 Neurons and 30 connections, hmm? Well, in the center (the big black circle) there's 11 little circles (or twelve if you'd call the third from the top on the left a circle.. looks like a mistake to me). Count all the lines going between these, and include the lines coming in from the left (the red ones) and the black one going to the big black circle and you have 30 lines.....
Anyone more knowledgable that I care to figure this one out?
---
- Give a man a fire and he's warm for a day, but set him on fire and he's warm for the rest of his life.
This thing is a joke. There are virtually NO ramifications for speech recognition, because it is virtually IMPOSSIBLE to build a neural net that recognizes 40,000-60,000 words! This stupid demo recognizes two (or in one case, four) words. Yes, No. Not much of an application there! Or at least, the applications are very limited.
File under: fluff. I work for a speech recognition group. We did.
I don't know, but if you read the article: "And the system can pluck words from the background clutter of other voices -- the hubbub heard in bus stations, theater lobbies and cocktail parties, for example." Now I've never been in the navy but I don't actually think that they routinely search for the sound of submarines in bus stations and cocktail parties. :-)
Consarn it!
This AI machine certainly has more neurons than I have delegated to speech recognition as I am in the process of patenting a process in which you can switch 95% of your brain capacity over to web surfing, useless pop culture quotes, and slashdot posting.
I figure if everyone was less intelligent, it would be way easier to create artificial intelligence.
I've recently done quite a bit of research on Neural Networks, including coding and simulating them by hand... There are some (qutie drastic) flaws with neural networks...
I started my research doing a classic 5 pixel by 5 pixel OCR (optical character recognition) on the domain of digits on a single layer perceptron type network (similar to what these guys were using minuns the delayed firing rate)
Not suprisingly, the training algorithm converged to an answer quite quickly and I proceded to run tests with noisy data, to test the genrealazation of the network.
This isn't shocking in itself until you realize that once you go above fifty percent distortion rates you are actually INVERTING the digit!
I retrained the network with inverted digits as well as the normal digits and re-ran the tests on the same set of data (note: The net WILL NOT converge on normal & inverted 5x5 digits with only ten cells).. The correctness rate was only twnety-per cent throughout the whole domain of noise levels.
I then retrained again using TWENTY cells (9 more than this articles) and it converge quite nicely and gave me a quadratic function with an R-Squared value of .9995 or so.
People view Neural networks sometimes as a fix-all solution.. The article on /. earlier about "eveloutionary computing" is the same premise as neural networks : try stuff randomly (or using calculus) until we get a decent solution.
I'm sorry kiddoes, but that just doesn't cut it. A neural network can't ever outperform a Turing machine so there can't be any chance in hell it will ever outperform us in non-specilized tasks.
Of course, I'd probably be more optimistic if these guys would have released there algorithms, papers, source-code, etc so we could actually figure out HOW the HELL they can get an 11 cell network to recognize speech...
The moral of the story? understanding speech is a hell of lot harder than recognizing ten digits!
Yeah the number of phonemes used in most languages is in the 'few dozen' range. And you generally don't have to listen very long to hear them all at least once.
But even when you've got the phonemes, you've still got a fair ammount of work cut out for you. A number of phonological processes take place. For instance 'in plain sight' in may be pronounced 'im'. These kind of transformations (and more complicated ones) are happening all over the place, in every spoken language.
Linguists generally describe this kind of thing by writing context-sensitive rules to enumerate the transformations. Similar syntactic translations are context-sensitive.
Computer programming languages' syntax (er, not counting types, and identifier agreement (which are special cased)) are not even typically generic context-free languages, but instead are almost always part of the LL(1) or LR(1) subsets, meaning that they have the special property that you can determine what's going on just by looking ahead one character. Otherwise you end up with N^3 parsing time, and that's for context-free languages. Parsing of context-sensitive languages is way more problematic (think halting problem).
Unless you can parse the syntax, you can't really resolve ambiguities (to/two/too, there/they're, or even things which merge because of phonology (bitter/bidder/bit her)). Note that humans don't do so great with these issues always either, so a partial solution will be still qutie amazing.
But the fact still stands that turing samples into phonemes is only the first step in a very complicated process towards even something as simple as taking dictation. In fact, I'd say that syntax->semantics may be a smaller step than phonemes->syntax.
Trees can't go dancing
So do them a big favor
Pretend dancing stinks!
I think the really important thing here is that the neural system almost certainly knew there were only four possibilities, and never had to respond 'none of the above'. So this is a comparatively simple two-bit classification problem, which is a far easier thing than what Dragon Dictate (or people) are trying to do, ie recognise a arbitrary string of phonemes, giving a combinatorial explosion of possible words. So the performance of this system probably is actually not that impressive.
But there is a huge interest building in biological neural networks' sensitivity to the temporal sequence of input spikes (rather than just the average rates of inputs spiking, which is what software neural networks try to model).
There was a talk I went to in London in June by Terry Sejnowski, who's head of the computational neurobiology lab at the Salk institute in California. Apparently, rather than neurons learning that signal A correlates with signal B (Hebbian learning), it's apparently surprisingly easy to wire two neurons up so that they are correlating signal A occurring just before signal B -- becoming more sensitised to this, the more times they see it, so they effectively they learn to predict signal B as soon as they see signal A.
This obviously appears to be very important for tracking objects at a low level, and as here in identifying temporal patterns (Sejnowski's suggestion was bats' echolocation); but it may be even more important at a higher level, for recognising causality (if this thing happens, then that good thing/bad thing) may happen, and perhaps for learned behaviour (if I do this, under these circumstances, then that happens).
Pulsed Neural Networks. It's really not such a new technology. There's a good book on different topologies and algorithms titled,
"Pulsed Neural Networks". I know Amazon has a copy (that's where I got mine a few months back).
And to produce the best over all listener, you would train it against random noise levels within a range (with a weight towards what it will be used for most). And if you want better performance, just throw some more neurons at it. Fidelity goes up.
It's 10 PM. Do you know if you're un-American?
Could this be true? Has science finally found a way to decipher Nirvana lyrics?
It seems like every single Slashdot article nowadays has several posts that inevitably link some new piece of technology with ways the evil government can spy on us.
Go e-mail 'michael' about it. I'm sure he'll be happy to write up another Your Rights Online editorial thing where all you folks can go discuss the latest evils between yourselves, but let's keep the conspiracy theories out of "normal" articles, OK?
TWW
Anyway, these results are _quite_ significant in that they really show an advantage to using this new type of NN, and also make it clear to people that if we integrate these sorts of sensors into ourselves, or an AI such as CYC (check it out...), the resulting system will be able to process sensory information much more effectively than humans...
Of course, we've always known that the vision of hawks is like a couple hundred times more acute than that of humans, but some people never made the connection -- If hawks have better vision, and they have NNs to process that data, and we can learn how to make good, well trained NNs, then our AIs can have better vision than us, based on a biological model...
And on a similar note, I think it's amazingly cool that they've been able to show that a neural net trained by humans for a special purpose can -way- outperform biologically evolved neural nets... :)
Oops, you're right, though you're not using the proper terms.
/su/ - I haven't looked at any spectrograms for a while, but I'll take your word for it that the /s/ sounds differ in quality. You could say that they are different phones. However, they are definately not different phonemes, in a strictly linguistic sense. Even if you know the difference, I'll explain it to everyone who doesn't have a Linguistics (or related) degree.
/si/ & /su/ example illustrate this nicely).
/si/ vs.
Any sound made by a human can be called a phone. Many of these crop up in language. These sounds can be classified into groups. These categories of sounds are semantically the same - switching from one s to the other does not alter the meaning of a word. These are called phonemes.
Some phones within a phoneme can be chosen by the speaker, these are said to be in free variation. Others are determined by context (and sound funny otherwise) - these are called allophones. (Your
Spanish does not distinguish between b and v, similarly to the way Japanese lumps r and l (two separate phones) together into what in Japanese is the same phoneme.
I omitted to mention this added layer of complexity - the sonic properties of a given phoneme (which is really what you want to extract, in order to build morphemes) can vary a lot, to a degree dependant upon the language, dialect, and accent.
Nice to see some other language geeks here - keep me on my toes.
Trees can't go dancing
So do them a big favor
Pretend dancing stinks!
...is the naive who think its impossible for this technology to be used for such reasons.
I don't think it would really affect it so much, if it does chances are its a bit slower in learning considering it uses timing. It seems more like its just has another dimension to it.
So, effectively, each node would be building up an internal estimate of a Markov transition probability, p(A->B given A); with the node's output the probability that the transition A->B had occurred; but with the added feature that different transitions are associated with different time intervals.
Clever !
Whether speech recognition has advanced greatly with this particular claim is yet to be seen. Powerful speech recognition, however, has many great potential benefits.
Science marches on!
When it really gets rolling, encrypted voice communication will be more of a necessity than a paranoid indulgence. Conspiracy theory? Try this test: Would you use this tech to spy on people?
When you say, "Dude, the conversation at the next table triggered my autogrep of the word 'computer'," you could be talking hardware instead of wetware autogrepping.
Imagine donning headphones and hearing only a computer-enhanced (probably a little time-delayed) version of the surrounding sounds where selected voices are augmented. The same tech could probably be applied to identifying and reducing known noises. Chatting at a dance club wouldn't have to be a shouting match. (But, then there's less excuse to get close to their necks...)
"Yes! No! Stop! FIRE?" I wonder who's sponsoring this, or to whom these researchers are whoring themselves... "Yes! No! Retreat! Use the nerve gas!" War marches on!
It's been said already, but man, I have to echo this. Practical speech recognition + language analysis & translation + voice synthesis will rock. Just imagine being able to hit on an lovely Italian by telling her that you like her hairstyle and that's she's a pretty lady: "A lot I appreciate your style of hats. You are one Mrs. much graceful one. Beep." A whole new era of international misunderstanding.
The idea of Ctrl-key-free chorded typing still excites me. I'll pop you in the speech-recognized mouth with my data gloves.
The moderation of this post to Offtopic shows that the Offtopic choice should be removed from the moderation list. Offtopic is a totally subjective choice and I can say that during the many many times I've been a moderator I've never used it. This post is not Offtopic, it should be marked Funny as it was clearly meant to be.
FYI, the phoneme-to-word (or, more generically, feature-vector-to-word) translation is conventionally done with Hidden Markov Models (in a nutshell, creating probability driven state transition models). I'd expect the commercial dictation products probably have a somewhat ad-hoc cleanup stage to post-process the HMM output.
Yet another comment from the conspiracy to make it look like there is only one conspiracy
/., just look at the stories on geek profiling (The Katz stories). The Government IS out to get us, they admit it after all, and what is this caused by? Paranoia on the part of people in power. It's a dramatic irony, of sorts. But the Light in the darkness and the shadow from the sun is manditory for everything in life.
Honestly, do we have anything to fear from the technology as it is now? No, of course not. However, you have to expect plenty of fear on the part of people from
This mass paranoia against governments isn't bred because someone reads Farenheight 451 and says "shock!", (although it probaly does happen in SMALL quantaties) It's because we see it in our government today. We see corruption, and special intrests, and all sorts of scary, scary things, in government TODAY. The fact that this could be used to track all of the recordings a person ever made is scary.
Is it a long way off? Sure. Can you blame them for being overprotective of their rights? No, of course not.
Nothing personal but I don't see how you can mock or make fun of anyone for holding these fears.
-[ World domination - rains.net ]-
Who needs a Palm Pilot when you can walk down the hall hands free as the briefs you on your next meeting, or allows you to read and compose your mail on the way to work. My hands shake.
:)
I wonder if that would be terribly successful. Apparently, the first car phones marketed were speaker phones, which sounded like a good idea because both hands would be free for driving. The idea flopped because people looked kind of odd talking to themselves while driving.
I bet there would be a similar effect (at least for a long time). People walking down the sidewalk talking to themselves usually get some pretty strange looks
Dana
I bet that the human John C. Dvorak is faster than a neural net.
White noise is certainly random - but background noise in real world situations is hardly going be that random. Rather, it's going to be a chaotic blend of non-random signals - each of which may (or may not) be a valid speech signal in it's own right.
;)
Actually it does not matter whether the background signal is completely white, or not. As long as the speech signal is the most correlated one, you can find it. The coctail party problem (to isolate one speech signal in a crowd of speakers) is of course more difficult. The technique can be extended to separate more sources, if one adds more microphones/ears (see independent component analysis), one extra microphone per source you want to isolate, but that would be to cheat, wouldn't it
Of course, I could be mistaken, and that drawing is really a graphical representation of the most sophisticated neural net ever made. *g*
--
remember that epside where they were stuck in the time loop and by like the 4th time around or so, Data was listening to some noise from Space, and he said something to the effect of "I can dicsern 1024 distinct voices" and it turned out to be the crew of the entterprise yada yada yada...but anyway, no HUMAN can dicsern that many voices that accurtaly (not even CLOSE!). Cool that computers can now do that :)
"There is no spoon" - Neo, The Matrix
This (the bit about timing of signals) is the sort of thing my father-in-law (Dr. Jack Steele) has been complaining about folks missing for years. (And he ought to know -- he invented the term "bionics" back about forty years ago.) (Gee, if he's the "father of bionics", does that make me the brother-in-law of bionics?)
I'm a little surprised at how few neurons and links it took, though - and how general purpose (as in different languages) it is. Different human languages contain somewhat different sets of phonemes - what may be two distinct phonemes in one language are considered the same in another. (E.g., Chinese has a sound between the "p" and "b" of English, considered differetn from either. Hence the difficulty anglicizing the name of the city Peking/Beijing.)
-- Alastair
Voice recognition wouldn't be of great use to me, at least at the desktop. I hate leaving prolonged voicemail messages because I can't go back and edit a previous sentence. I have to go and compose a speech if I want to sound intelligent and coherent.
Voice recognition only becomes useful to me if natural language parsing and enough cognition power are available for me to command my computer in plain english to a fair degree of abstraction.
In mobile computing, it might be a lot more useful, especially for a device, say the size of the Palm Pilot, where various factors make voice far more convenient and less difficult than other forms of input.
There are a lot of human use factors that complicate voice recognition (making the computer recognize when you want it to parse your speech and when you don't want it listening). Human interface issues often make these things less wonderful than they appear.
Not that I'm saying this isn't a wonderful development and there aren't people out there who could really use this (in specialized environments or people who have mechanical difficulties), but I don't think voice recognition is going to change the world the way some people think it will.
Use more neural nets.
Some people are saying that you can't make a really big neural net efficiently (at least without specialized hardware), but I don't see why you couldn't have hundreds of seperate neural nets each reporting on whether one word was said.
A very tiny, very simple computer could handle the task of managing a few neural nets. You could make it out of a few thousand surface features on a chip, so you could pack thousands of these processors on a chip. For that matter, they probably don't need to be terribly fast, so you could make them like memory chips. Imagine a megabyte chip, but instead of 1024K dumb memory, with 1024 minimal neural processors, each with 512 bytes of RAM.
Broadcasting the incoming data is pretty simple, and I don't think the networking issues of one or two of these processors reporting every few seconds would be too severe.
Training wouldn't be all that hard, either. You need a few man-years of samples, but the training could be done in parallel. It would cost a few million dollars (unless there was a dedicated online effort, which is entirely possible), but not billions. Imagine going down to the mall and asking people if they would read a few hundred words for $20; no problem, just repeat it all over the place so it deals well with accents.
There has never been a task better suited to massive parallel processing.
Oh yeah, I suppose I have to say: hey, we can do it with a Beowulf cluster, |)00|)Z!
To all of you naysayers out there who think this system has no real-world use because it can only understand a handful of words...Do you so easily forget the lesson of the computer? You only need two states to transmit information. If we merely learn to speak in binary (On On On Off Off On) the problem is solved and we have achived practically perfect speech recognition. Narrow minded fools!!!
That's the second comment today that slipped through the error check with an error. The first sentence should read:
:-)
"If any choice was to be removed..." You can't moderate a choice
/* Steinar */
(This comment is of course GPLed.)
Well I read the article as someone posted it, it certainly is intriguing. Dont get me wrong about this being cool, it just seems (to me at least) that using the brain to out perform the brain is an odd assertion.
Of course computer control via voice would generally happen in a controlled environment and would probably not have to involve a huge vocabulary as long as the computer could be trained on basic phonics and cross reference against a good dictionary.
-Rich
Come on, why would always the military be `5 to 20 years ahead of' civilian technology? Remember, there _are_ great people outside the military as well. And there are more of them. Sure, the military can `take' tech from civilian life and not the other way round, but still? (BTW, there are _many_ militaries in the world...)
/* Steinar */
(This comment is of course GPLed.)
If you can get a computer to use them correctly more than 80% of the time? You can't even get slashdot posters to do that. What a bunch of loosers^H^H^H^H^H^H^Hlosers
--Anonymous Cowlings
That's the sunroof for the Oscar Mayer Wienermobile! :P
Please! If they really wanted to test the capabilities of this system in comparison to a human, they should use my wife!
Her: Honey, where are you at, its so noisy? And who is that with you?
Me: Um, nowhere and nobody, its just a business meeting...
Her: Oh? Does she work with you?
Me: Um, who?
Her: The 26 year old brunette wearing the green dress who just said your name two tables away. I'm not deaf, you know...
Deosyne
There seem to be a bunch of people saying how great it would be to use voice commands for their Linux HCI, so I thought I'd let them know that you can do it already, just download ViaVoice for Linux (beta) free from IBM, then get Xvoice by Dan Creemer. Xvoice allows you to send your speech (which is converted to text by viavoice) to any X application as a stream of synthesised Xkeypresses. If you're interested, I'm trying to develop some grammars for X apps like the terminal, netscape and Xemacs which would permit speaker independent voice recognition for command sequences, and I could use some suggestions from the people who'll be using it in the end so that I'm not developing in a vaccuum. Tom Doris. Remove 'nospam.' to email: tdoris@nospam.compapp.dcu.ie
Are your research materials online?
I like following the progress of projects around the world --- I was in academia myself a decade ago, in a department where colleagues who were working with NNs would discuss their processing requirements and architectures with me. The work you describe sounds interesting.
"The question of whether machines can think is no more interesting than [] whether submarines can swim" - Dijkstra
Probably the single most important item on /. this year, if not ever. This has earthshakingly profound implications. Still not genuine AI, but the path is clear, to those with eyes and ears. No patent, though. There is ample prior theory, if not art, but it's lain acknowledged and unrecognized for a long time. Totally apart from the fact that this is fundamentally a discovery, not an invention. Any patent issued would be subject to irrelevance by a more general statement of the issues at hand. Patent is a legalized form of theft, anyway, and I would only say that there are those who are not averse to larceny in turn, in a just cause. Sorry to be cryptic, but any plainer would be asking for trouble. That's not to say that kudos aren't in order.
You might also want to check on John Hopfield's group in Molecular Biology at Princeton, who have also been demonstrating word recognition in noisy environments, based on neurons receptive to the timing differences between action potential spikes.
I can't see any papers online, but I think there were papers at NIPS the last couple of years.
As far as I remember, he had basically got the neurons to do a time-frequency decompostion, which automatically rescaled to allow for different speed and pitch baselines, and could use the outputs to train an adaptive classifier.
Hopfield was pretty pleased with the results, but one guy from the speech community was very unimpressed. His line was that distinguishing a small number of well separated possibilities was not hard, so almost any technique would do well. (That is basically what you're saying above). But that doesn't tell you anything useful /at all/ about how well it would identify a word from the full range of possible speech, because from a limited number of very distinctive words we get no idea how similar those likelihood ratios might be for other words. In fact, once you're looking at the full range of speech, different words can be very similar, and it has been /very/ difficult to push up the likelihood ratios even to present levels of discrimination.
So performance on such a small set of possibilities really tells us nothing about the real efficiency or effectiveness of the USC techniques.
White noise is certainly random - but background noise in real world situations is hardly going be that random. Rather, it's going to be a chaotic blend of non-random signals - each of which may (or may not) be a valid speech signal in it's own right.
--
Clear, Dark Skies
And I bet it could be done in 2 lines of perl!
My Freakin Blog
That's OK. Once the machines can out think us, they'll probably exterminate the entirety of humanity anyway, so you really don't have to worry about Big Brother at all.
I'm trying to teach myself to set people on fire with my mind... Is it hot in here?
What I don't get is what are all you people saying that you're afraid the guv'mint is gonna hear? I doubt they're really interested in your shopping lists.
... never mind. I understand now. :-)
American paranoia makes me wonder - America is an elected democracy last I heard, so why are its citizens so afraid of the people they've elected?
Oh wait...
Bill Clinton - Openly lies.
George Bush - Former CIA head
Ronald Reagan - Alzheimer's sufferer
Handsfree carphones flopped? Well, they are compulsatory in the Netherlands now. It's illegal to drive and use a non-handsfree phone in your car.
Living is a horizontal fall
Remember in _Snow Crash_ when YT flipped her phone open, said her boyfriend's name into it, and it looked up his number from its memory and dialed it? This technology looks to make that kind of thing possible. Personally, I think that'd be great! You could type someone's number into your cell phone once, then speak the name you wanted to address them as to "train" the phone. From then on you need only speak their name into your phone and it'll automatically dial their number for you. Uber-convenient and dead simple. It sure beats the hell out of trying to type in a person's name via a telephone keypad. (Assuming your current cell phone even allows you to do that - mine doesn't.) I don't care about larger applications, or the AI potential, or any of that big picture stuff. I just want to be able to say "Mom" into my cell phone and have it dial her number. This could be an absolutely killer application, and make tons of money for the first cell phone company to license and perfect this technology. With only 11 neurons, you know it's got to be cheap to fab into silicon and put on a chip. -Ben
Tinker-toy topologies (lines & circles) don't usually give enough info to figure out what they're doing. The real meat is in the weight update (training) algorithm, and the detection algorithm, but in this case we get a few clues.
Though it is interesting to note that it looks amazingly non-dynamic -- the 5th output neuron looks to be the only feedback neuron into the hidden layer. (Voice recognition nets usually have lots of feedback connections to refine the net's guess based on constantly-incoming data AND previous iterations.)
Which would leave the four other output neurons to be the "four words" that it can learn... Which means the fifth neuron (the feedback) is probably an "I don't know" output.
The input signal appears to be sent through 5 bandpass filters & then on to the input layer.
Another interesting feature is that it's not a fully connected trans-layer net... which can save time on large NNs, but it can be like severing connections in your brain--you don't go doing it willy-nilly.
My guess is that they custom-created this net to get the results they wanted and that it won't scale for crap.
The article alludes to the US Navy's hope that the technology can be applied to detecting and classifying ships' and submarines' sonar signatures more quickly and reliably. In spite of the bitchin' signal processing the Navy already does, it's still as much of a black art as a science. (Like the old joke about how to get to Carnegie Hall, you have to practice, practice, practice!) I wonder what a massive infusion of neural-net processing will add to the AI end of it. Same thing goes for ELINT/ESM and radar-intercept work -- I wonder how much better we'll get and how quickly.
"How many light bulbs does it take to change a person?" --BMcC-->
Does anyone know if these results scale up to a large vocabulary? The better-than-human recognition results are really stunning, but a traditional problem with auto speech rec is sparsity in the training set, isn't it? Does anyone know if it will still work with 20,000 words in the vocabulary, and how much training is required to get there?
I am not a Ph.D in this field, but I do have my Master's degree in Speech Science. While I have taken a break from Speech Science for about 2 years to learn C++ enough to start working in computer speech recognition/perception/production I'm still fairly up on Speech research. That caveat out of the way, let me tell you my thoughts.
/s/ phoneme, but the one in /si/ ("See") has a spectrum much higher than (well, in speech terms, I think about ~1KHz) /su/ ("Sue"). Phonemes are not discrete things, they are gradients or classes. So you are simplifying things far too much when you suggest that morphemes are just combinations of a few dozen phonemes.
/s/ in /si/ vs. /su/) as one thing that can cue a listener into what phoneme follows it. In that particular set of studies, people were able to identify the morphemes (/si/, /su/, etc.) by only hearing the initial /s/. That is, the vowel was cut-off from the morpheme, yet people were able to (with something like 90% accuracy) complete the morpheme.
While you say there are only a few dozen phonemes in most languages what you are missing is the fact that each phoneme is context sensitive. So if I say "See" and "Sue", the 's' sound in each morpheme is spectrally quite different. They are both the
Really, if you think about it, humans do not learn to understand words by rote memorization of the acoustic properties of each word. That would be far, far too inefficient. Think about the fact that you could still understand someone's voice, even if they inhaled helium. That skews the spectral/acoustic properties of the person's voice into a very high frequency range compared to their normal voice. Also, if you tried to listen to non-native speakers who are missing phonemes or substituting phonemes, how could you possibly understand them? What you do is you figure out the missing or corrupted phonemes from the context of the morpheme. Some research supports the addition of other, extraneous acoustic information (such as the spectral shift of
There is an awful lot that speech research has not yet uncovered. One of the problems that I see in the field of computer speech recognition/perception/production is the lack of solid speech research and implementing the trickier research into these projects. Training neurons to recognize individual morphemes doesn't work. It's like brute force calculation of chess; the system is too complex to tackle with such a simple model. It's just too damned inefficient.
Besides, homophones will always be a problem with speech research, until language makes an appearance. How many times do you want to have to correct "their", "there" and "they're" in a document?
---------The early bird gets the worm, but the second mouse gets the cheese.
No problem with that... just that many more people will leave you alone when you walk down the street :)
Get a life, not a lifestyle. - Hikem Bey
I cant seem to get there.
Sounds like some pretty dubious claims that some neurons can out do a human brain. Anyone here who can post a summary?
-Rich
"Just once, I'd like to meet an alien menace that wasn't immune to bullets." -- The Brigadier, Dr. Who
Contact: Eric Mankin (213-740-9344)
l /real_video.html
l /real_video.html
Email: mankin@usc.edu
Release number: 0999025
Release date: 9/30/99
A demonstration of the Berger-Liaw Neural Network Speaker-Independent
Speech Recognition System can be found on line at
http://www.usc.edu/ext-relations/news_service/rea
Jim-Shih Liaw (left) and Theodore W. Berger (right)
Photo by Eric Mankin
Machine Demonstrates Superhuman Speech Recognition
Abilities
University of Southern California biomedical engineers have created the world's
first machine system that can recognize spoken words better than humans can. A
fundamental rethinking of a long-underperforming computer architecture led to
their achievement.
The system might soon facilitate voice control of computers and other machines,
help the deaf, aid air traffic controllers and others who must understand speech in
noisy environments, and instantly produce clean transcripts of conversations,
identifying each of the speakers. The U.S. Navy, which listens for the sounds of
submarines in the hubbub of the open seas, is another possible user.
Potentially, the system's novel underlying principles could have applications in
such medical areas as patient monitoring and the reading of electrocardiograms.
In benchmark testing using just a few spoken words, USC's Berger-Liaw
Neural Network Speaker Independent Speech Recognition System not only
bested all existing computer speech recognition systems but outperformed the
keenest human ears.
Neural nets are computing devices that mimic the way brains process
information. Speaker-independent systems can recognize a word no matter who
or what pronounces it.
No previous speaker-independent computer system has ever outperformed
humans in recognizing spoken language, even in very small test bases, says
system co-designer Theodore W. Berger, Ph.D., a professor of biomedical
engineering in the USC School of Engineering.
The system can distinguished words in vast amounts of random "white" noise -
noise with amplitude 1,000 times the strength of the target auditory signal. Human
listeners can deal with only a fraction as much.
And the system can pluck words from the background clutter of other voices -
the hubbub heard in bus stations, theater lobbies and cocktail parties, for example.
Even the best existing systems fail completely when as little as 10 percent of
hubbub masks a speaker's voice. At slightly higher noise levels, the likelihood that
a human listener can identify spoken test words is mere chance. By contrast,
Berger and Liaw's system functions at 60 percent recognition with a hubbub level
560 times the strength of the target stimulus.
With just a minor adjustment, the system can identify different speakers of the
same word with superhuman acuity.
Berger and system co-designer Jim-Shih Liaw, Ph.D., achieved this improved
performance by paying closer attention to the signal characteristics used by real
flesh-and-blood brains in processing information.
First proposed in the 1940s and the subject of intensive research in the '80s and
early '90s, neural nets are computers configured to imitate the brain's system of
information processing, wherein data are structured not by a central processing
unit but by an interlinked network of simple units called neurons. Rather than
being programmed, neural nets learn to do tasks through a training regimen in
which desired responses to stimuli are reinforced and unwanted ones are not.
"Though mathematical theorists demonstrated that nets should be highly effective
for certain kinds of computation (particularly pattern recognition), it has been
difficult for artificial neural networks even to approach the power of biological
systems," said Liaw, director of the Laboratory for Neural Dynamics and a
research assistant professor of biomedical engineering at the USC School of
Engineering.
"Even large nets with more than 1,000 neurons and 10,000 interconnections have
shown lackluster results compared with theoretical capabilities. Deficiencies
were often laid to the fact that even 1,000-neuron networks are tiny, compared
with the millions or billions of neurons in biological systems."
Remarkably, USC's neural net system uses an architecture consisting of just 11
neurons connected by a mere 30 links.
According to Berger, who has spent years studying biological data-processing
systems, previous computer neural nets went wrong by oversimplifying their
biological models, omitting a crucial dimension.
"Neurons process information structured in time," he explained. "They
communicate with one another in a 'language' whereby the 'meaning' imparted
to the receiving neuron is coded into the signal's timing. A pair of pulses
separated by a certain time interval excites a certain neuron, while a pair of
pulses separated by a shorter or longer interval inhibits it.
"So far," Berger continued, "efforts to create neural networks have had silicon
neurons transmitting only discreet signals of varying intensity, all clocked the way
a computer is clocked, in beats of unvarying duration. But in living cells, the
temporal dimension, both in the exciting signal and in the response, is as important
as the intensity."
Berger and Liaw created computer chip neurons that closely mimic the signaling
behavior of living cells - those of the hippocampus, the brain structure involved in
associative learning.
"You might say, we let our cells hear the music," Berger said.
Berger and Liaw's computer chip neurons were combined into a small neural
network using standard architecture. While all the neurons shared the same
hippocampus-mimicking general characteristics, each was randomly given
slightly different individual characteristics, in much the same way that individual
hippocampus neurons would have slightly different individual characteristics.
The network created was then trained, using a procedure as unique as the
neurons - again taken from the biological model, a learning rule that allows the
temporal properties of the net connections to change.
The USC research was funded by the Office of Naval Research; the Defense
Department's Advanced Research Projects Agency; the National Centers for
Research Resources, and the National Institute of Mental Health. The university
has applied for a patent on the system and the architectural concepts on which it
is based.
A demonstration of the Berger-Liaw Neural Network Speaker-Independent
Speech Recognition System can be found on line at
http://www.usc.edu/ext-relations/news_service/rea
EM.BERGER99
University of Southern California News Service
3620 South Vermont Avenue, Los Angeles, CA 90089-2538
Tel: 213 740 2215 Fax: 213 740 7600
Email: news_service@usc.edu
WWW: http://uscnews.usc.edu
Napster-to-go says "Fill and refill your compatible MP3 player", which is a lie. It's not MP3. It's WMA with DRM.
I am very excited by the possibilities of this technology. Just imagine it: a really good speech recognition system coupled with a really good natural language analyzer coupled with a good speech generator. What do you get? The comm/computer system from Star Trek:TNG. Hell, there's probably enough "Computer Voice" samples of Majel Barrett to at least give the speech generation software a good starting place.
Who needs a Palm Pilot when you can walk down the hall hands free as the briefs you on your next meeting, or allows you to read and compose your mail on the way to work. My hands shake.
My only concern: the people who design this system would need to included Star Trekish terminology and attitude into the list of things the computer could do. Example:
--
"Computer, please replay voice mail message 9 starting at time index 0-mark-9-5."
[computer chimes, message plays]
"Computer, message 9 sounds garbled. Run a level-three diagnostic on message integrity."
[pause]
"Diagnostic complete. Message shows signs of type-1 file corruption."
"Damn it!"
"Error: cannot comply with that directive"
--
If we could just get that far, then I'd be happy. Actually, no that's wrong. If we could just get that far, then invent warp drive, replicators, transporters, inertial dampeners, and holodecks, *then* I'd be happy.
Ross
Check www.inplainwords.com - that's a cool language understanding website
The article misses another interesting, albeit scary, use of this technology. If these could be made small enough and cheap enough, they could be placed in key locations across the country, forever listening in on passers-by.
Avoiding all the issues of privacy, consider the following scenario. The police want to arrest a suspect for some crime (drug traffiking, conspiracy, etc.) but have no proof and can't tap his phone lines since he encrypts all his phone conversations. Through some method, they train this speech-recognition device to the suspect's voice and either have someone with the device planted on them track the suspect or have an array of said devices placed in public areas where the suspect is known to hang out (bus terminals, bars, etc.). Sooner or later, the suspect might slip up and the authorities have enough evidence needed for an arrest.
Regarding privacy concerns, it seemed to me that this device could only track a handful of known voices ... probably requiring vast processing power to track every voice in a room. So it might be a while yet before everybody's conversations in bugged places get transcripted.
Damned cool technology, though.
ian
Dosent anyone ever consider the "God Factor"?
I mean, you have DARPA with a new toy, and head shrinkers that have a new tool. And all the time that i was reading that article, i was getting the feeling that people were glorifying themselfs, when they were really just mimmicking what they already saw with the human brain.
Soon we'll see scientists with more neural nets, and the creator of the first one that says "I'm Sorry Dave" will think he is god.
This may sound like just a bunch of preachy BS, but it's very disturbing...
--
BlackSpyder
And the gods of Rome and Greece and Egypt all cried out in vain, for noone could save them from their own distruction.
What is special about this technology is not _what_ it does. As several people have pointed out, speech recognition (at least the single word variety) is old hat. IBM had speech recognition technology working marginally during the days of the 386en.
What's special about this technology is _how_ it does what it does. I appreciate those of you who pointed me towards that HP Palmtop with speech rocognition built in, but guys, look at the specs! A 133MHz processor and 32 megs of RAM. Christ, you could practically run DragonDictate on that thing!
This new technology is different because of the amount of processing power and memory (both code and RAM) it takes. You can't run DragonDictate (or any other software based spech recognition stuff) on a cell phone. The CPU power simply isn't there. And if you put it here, it would kill the battery life so severely as to render the cell phone useless. I'm not even going to get into the size and heat issues.
But this new technology does give us the ability to do something we couldn't do before. It allows us to embed low-end but still accurate voice recognition into portable, battery powered devices. And _that's_ what's cool about it.
-Ben
So long as it's instruction is good, it's french (or German, whatever) will also be good.
-- The One and Only NotMike.
user types: FORMAT C: computer: ALL DATA ON DRIVE C: WILL BE ERASED ARE YOU SURE? user says: nooooooo!!!! computer response (using linux(I know that it's really /dev/hda1): FORMAT CANCELED computer response (using windoze): FORMATING DRIVE C: ... this would be cool for when the computer asks for conformation (yes, no, yes to all, cancel) or something.
"throwing more neurons" into a neural network does not necessarily improve its capabilities. Well, it kind of does. It increases its capabilities to learn special cases, but can often reduce it's ability to learn generalities - if it can memorize that f(2) = 4 and f(3) = 9, it may have a harder time realize that f(x) = x^2.
The more neurons you have the more heterogeneous your training data must be.
Trees can't go dancing
So do them a big favor
Pretend dancing stinks!
I have to wonder, one of the major basis for the success of neural networks is that they are trained, rather then programmed in the traditional sense. This works fine while your researching and developing a singular system. But how do you mass-produce these systems? You can't just apply the same code across millions of them. Will there be classrooms filled with little computers learning how to be computers? What happens if one becomes a bully? What if one can't do math? And will there be trauma counselors on hand should one Blue Screen?
Dear Sir/Madam
I am writing to inform you that your network failed to show up for English Class today. We cannot stress enough how important regular attendance is key in achieving a proper education.
Please attend to this matter as this is its fourth missed class.
Thank you,
011100110
Principal - School of Advanced Network Training
"They do not preach that their god will rouse them, a little before the Nuts work loose." Kipling, 'The Sons of Martha'
Relax. Some neurons can outdo a human brain for a specific, limited function. Note especially that according to the article, it was "benchmark testing using just a few spoken words".
Presumably it'd take a larger neural net to deal with tens of thousands of words. Though it's possible the concept could be extended to that level.
And why not?
...OR speech recognition to write mail with your voice. Actually, people are doing it today, via a very cool tool. It's called ASAACP (A Secretary And A Cell Phone) ;-) Yup, some do it... Not saying that it's not weird...
/* Steinar */
(This comment is of course GPLed.)
Actually, some slashdotters are using english at a level less than 80% correct ... so if you translated that to french, it would be about 64% correct.
Maybe we should just stick to pointing and grunting.
Yeah, _first_ run it through a recognition process (at let's say... 95%), _then_ through Babel Fish (which has an accuracy of about 30%... if you're lucky), and then through some speech engine, which probably has an accuracy of 1%.
;-) At least with today's technology. I don't think this recognition stuff is ready for the masses before at least a few years have passed... Sounds like I'll just stick with the fish in my ear for now... ("Come on, it's only a little one...")
Sounds like you would get a close to _minus ten percent_ (OK, it's not negative...) translator to me
/* Steinar */
(This comment is of course GPLed.)
A good point, but maybe the long involved process they used in the lab can be automated somehow. Lab work is sometimes like that. Some gruntwork is necessary to set up proof-of-concept, but there are often ways to speed up the gruntwork if the p-o-c gets you sufficient funding.
Sure, English might have a million words, but I doubt you will use more than 1-2% of that in daily life. A system taking the 10-20000 most common words would be more that good enough for most uses. Typing (or guessing, if you're not using it for dictation) that occasional weird word (like `Slashdot' :-) ) wouldn't be too much of a nuisance anyway.
/* Steinar */
(This comment is of course GPLed.)
Although this article is impressive, realize that the ability to pick out words is entirely different from the ability to understand words, to use words. I would bet that a 2 year old baby still has better comprehension and understanding of ideas expressed by spoken words than this nerual net does. Think of the way our language evolves, all the slight variations in tone and in gesture(sarcasm anyone?) , regional dialects (it's like butta) and all the double meanings of words (cleave). Mind you this stuff is pretty neat, but we have a long way to go before we can have conversations with our computers. Even then, I would rather talk to a two year old, i'm sure they hold the secrets of NP math in their little brains, they just forget it all during their Power Rangers phase.
If you read down near the bottom of the article, however, you will find this:
"The network was configured with just 11 artificial neurons, and in a sub-stage a live goat brain. The brain was activated through a patented process involving a castle and a lightning storm.
The researchers said one day they hoped that all humanity could benifit from the power of lighting.
Then they laughed kind of ominously."
Hotnutz.com
This makes me start to think about the translation AIs used in Kim Stanley Robinson's _Green Mars_. If it can recognize language, then it could pump it through a translator, and out the other side could come 80% correct french. That would be kinda cool. :)
There is no silver bullet. Plus, werewolves make better neighbors than zombies or vampires anyway.
Terminologies, dialects, genders and whatnot would (will) be user-defineable, much like WinAmp skins or QuakeWorld skins. You'll have endless variations of the Star Trek Theme (including the charming and original fembot monotone from the original series), the Gangsta Theme, the Sesame Street Big Bird Theme and, of course, my personal favorite, the Wicked British Nanny Theme.
"You have 3 tasks left incompleted on your to-do list, you Naughty little boy! This calls for a vigorous spanking!"
(whipcrack) GrrrrrrOWl!
**>>BELCH
Come on! This is _the_ coolest piece of technology I have ever seen. Yes, there is the "big brother" possibility, but we shouldn't discourage a technology solely on that merit. Think of what this could do for deaf people! A pair of glasses that gives a text overlay of every (or certain) conversations in the room. Think how cool it would be to have your MP# library hooked up to a voice recognition system (yes.. ala trek). From what I understand, this system could still here your requests even when you had your music blasting. Talk about simplifying computer interfaces. Forget all this GUI crap!
In addition to the other good comments posted regarding taking this announcement with a grain of salt, I must add that the new system can only recognize a few words -- with only 11 neurons, it couldn't do much else. Without further information, I would guess that training up a net to recognize more words would be quite complicated -- especially given the non-standard training algorithms that were used. It would be great to find a scientific paper written by the researchers on the issue instead of solely press-release material. -dandre
On the other hand, this could be a great leap for neural networks in general. Realizing that the timing of synapse signals is a critical factor in neuron firing is going to shake up some things in AI. (At least, I was never familiar with neural networks that used timing cues. If I am wrong, please let me know.) Of course in a large neural network, you're going to have lots of propagation latencies as signals bounce around the net, and it makes sense that even more important than which neurons fire is when neurons fire. It actually seems to justify the complexity of neural nets because the timing data can represent a much larger data/search space than the simple fire/dormant state of each neuron.
This could be exciting.
My Freakin Blog
While the press release doesn't say much about neural networks or whether the state of the art in speech recognition has improved, it tells us something about a disregard by USC for standards of scientific conduct: scientific publication by press release is improper.
Unless there have been some recent changes that I'm not aware of, Echelon is not affiliated with NATO (in fact, many of NATOs members are spied on by Echelon). It is a network run primarily by intelligence agencies of UKUSA alliance - USA, UK, Canada, Australia and New Zealand (as well as a few other minor partners who give some contribution). It is well known that Echelon can search through internet traffic and fascimiles (among other "written" forms of long-range communication) for keywords, but at the current point in time it is unclear whether Echelon possesses the ability to do the same with telephone conversations via some form of speech recognition. An EU report from earlier this year seemed to indicate there was little evidence of this.
If you have two hypotheses e.g. A and B, corresponding to 'two words' which were said, then it is easy to build systems which can recognize signals corresponding to A and those corresponding to B embedded in lots of noise. Basically you measure the likelihood ratio p(B)/p(A) using some sort of estimators that you've trained to light up with either A or B. If you gave me the data, I could do this with a number of different semi-conventional numerical techniques on a digital computer. I've seen similar things presented at conferences a few years ago---recognition of specific chaotic waveforms (specifically dolphin and whale song) embedded in lots of noise.
This is known as a "simple hypothesis test".
The more general circumstance, however is that the alternative is not A vs B, but A vs a huge multitude of other possibilities. This task is much more difficult, and correponds to the actual large-vocabulary speech recognition task. Now it becomes much more difficult to set a reliable threshold which will come on only when A is actually present, and not when A is absent. There is a tradeoff of false negative and false positive errors depending on your choice of threshold.
There is no possible way that this thing can recognize 50,000 words. There are only 30 connections, there is fundamentally not enough information processing power intrinsically in there.
What you would do is to have all sorts of these subunits lighting up their own 'word finder lights', and the result of *those* (i.e. the p(A) detectors) would then be inputs into higher level semantic networks of perhaps a similar type. These networks or hidden markov models or whatever are the ones that know which sorts of words follow other sorts of words, and thus let you get better recognition than the individual word finders themselves.
So, what is the accomplishement of this paper??
That they've apparently found an extremely efficient and well-performing low-level subunit using this time-domain information. From our own experimental observations (not on speech but on real live neurons from recently-living animals) this is very important. The fact that it is only 30 connections might mean that it is quite feasible to put 10 or 20 thousands of these subunits on a single chip, running in hardware. Given the factor of a thousand speed increase of electronics over neurons if you could time-division multi-plex different recognizers (blue sky dreaming here!) you could have that much many more of them during the milliseconds to seconds of audio-frequency processing time that we speak at.
If you notice, Professor Berger said that no other speaker-independent system outperformed humans, even in small test bases. Presumably that means in the small Bayesian post-hoc sorts of likelihood test regimes taht I described before. And in addition, it appears that this is not a simulation but that they built it on an actual physical computer chip, another very substantial advance.
My colleagues are going to ask the authors for the actual paper. The title and press release may be overblown, but this smells like real science and a significant advance here to me.
Take home message: even small groups of good neurons can do interesting and useful things. With the right architecture, a small group of neurons can outperform conventional "neuroid networks" of hundreds or thousands of nodes linked by linear transformations of sigmoidal basis functions. We may just be beginning to crack real-AI.
We see major body functions of lower animals being regulated by say ten neurons. Real neurons are much smarter than you think. :)
If small groups of neurons can do this, it makes you appreciate what a hundred billion might be able to do.
If you live in the US, please take the time to thank your Federal Reps. for allowing federally funded researchers to patent federally funded inventions.
It has been done, as a handicap aid for neck-down paralysis. However, it's slow, and it's "just" cursor control with an on-screen keyboard. (Still, with a retinal display, it could be cool, as long as you're up for huge amounts of training.)
The military silences inventors in the private sector. - Anonymous silencee
i have typing disease
Certainly the spy agencies and secret police (yes, I include DEA FBI etc :-) will get these first, but it won't be long after they are available to everyone, and cheap too. (As an aside, the recent news about the Canadian cell phone company kowtowing to the FBI wiretap rules just amused me; it won't be long before computers the size of buttons will be able to be phones under Linux control, and there's bugger all the FBI can do about it.)
So now choose your favorite target: reporters planting these all over city hall, civil rights activists planting them around the local police stations, and nationwide -- ah, imagine the juicy into to come out of the national level bureaucracies, Congress, the FBI and DEA themselves...
It's the same with The Diamon Age motes floating around, David Brin's ubiquitous cameras, and so on. The big guns will have their monopoly for a very short time, and then they will have the last surprise of their very snoopy life.
Life will be really interesting. This is definitely a multi edged sword!
--
Infuriate left and right
Now I just need to upload my neural patterns to a more complex version of this, and voila! Mind Children!
Ok, yes the technology can be used to snoop, but just imagine combining it with some of those new glasses that project an image into your eye, you could instantly search the Net for supporting information for the conversation. If you think thats nuts, I now have telephone conversations and use search engines when I cannot recall something, which really freaked out someone the other week when we were talking about old TV programs and I couldnt remember the name of the actor in Max Headroom so I searched and found it was Matt Frewer while still chatting.
Any sufficiently advanced man is indistinguishable from God