Slashdot Log In
Vista Speech Recognition Goes Awry
Posted by
CowboyNeal
on Sat Jul 29, 2006 08:25 AM
from the egg-on-face dept.
from the egg-on-face dept.
An anonymous reader writes "It seems even MSNBC is willing to take a jab on those rare occasions when Microsoft products don't work. During a demo of Vista's speech recognition technology, Vista couldn't differentiate between mom and aunt, and all attempts to rectify the problem just made it worse. Wait until you see what it spat out, I think we have a new 'All your base.' Don't you just love Microsoft's live demonstrations?"
Related Stories
[+]
Your Rights Online: Microsoft Patents Frustration-Detection System 223 comments
I Don't Believe in Imaginary Property writes "Microsoft has patented a frustration-detection help system that would monitor your computer use and biometrics to figure out when you were frustrated. It could then offer to pair you up with someone else doing exactly the same thing who might be able to help you out. Interestingly, they don't appear to use speech recognition to detect abnormal levels of swear words, but that could be due to their past difficulties with speech recognition. 'Physical responses aren't the only things that could trigger this event--taking an abnormally long time to complete a task would do so also--but the biometric aspect is certainly the most unusual. Is this patent a harbinger of a dystopian future where computer users' biorhythms will be monitored to increase efficiency? Unlikely. The idea, which was birthed at Microsoft Research, is simply a more advanced version of user focus group testing that Microsoft (and most other software companies) have been doing for years now.'"
This discussion has been archived.
No new comments can be posted.
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
Full
Abbreviated
Hidden
Loading... please wait.
Roald Dahl (Score:5, Funny)
Reminds me of the Roald Dahl short story about the ant-eater who ate someone's aunt because their accent rendered the two words the same.
I can't remember what the story was called.
Re:Roald Dahl (Score:5, Informative)
Parent
Awww...c'mon guys.... (Score:5, Funny)
I mean, it's not like they have a reputation for releasing half-assed code that's been hyped up through marketing to the point that it will never perform as advertised.
And it's not like this is a company that is having image problems due to its monopolistic nature.
Or headed by an infamous ragaholic with a history of intolerance towards free standards.
Nope, I'm sure that this is just an accident by a company that spends its off hours petting little baby chickens and bunnies.
Re:Awww...c'mon guys.... (Score:5, Insightful)
This was really a dreadful presentation. There was no ambient noise (as the commentators say later, and despite what Microsoft says), and there was no echo as the demonstrator claims during the actual test. It seems to have been done under really good test conditions, but still it failed miserably.
Parent
Re:Awww...c'mon guys.... (Score:5, Insightful)
Voice recognition requires some training regardless of who provides it. We're not Star Trek here....Prep work and rehearsal people. If mr. sales guy had tried the demo before the presentation he would have noticed it wasn't working and avoided the embarassment.
This is why sales people are asshats. They're unprofessional non-technical people who sap back the high life while the rest of us have to put up with the mess they create through their daily barrage of verbal diarhea.
Tom
Parent
Mr. Pogue begs to differ: (Score:3, Interesting)
Reason 1: You don't have to train this software. That's when you have to read aloud a canned piece of prose that it displays on the screen -- a standard ritual that has begun the speech-recognition adventure for thousands of people.
I can remember, in the early days, having to read 45 minu
Re:Awww...c'mon guys.... (Score:4, Interesting)
A far more likely scenario, in my mind, is that he trained and tested it 100 times and got it working nearly flawlessly, but in a different room and with a different setup. In fact he may have overtrained it. Programs like this can behave very badly when they end up overfitting the data.
On the day in question he may have had a different mic and the acoustics were certainly different and the program went whacko.
Parent
Re:Awww...c'mon guys.... (Score:4, Insightful)
I seriously doubt this presentation was rehearsed. At the very least, they should have tested it in that room with that mic, etc. But in all honesty, this is going to be used by millions of people in all sorts of rooms with all sorts of mics. That shouldn't matter anyways.
Anyways, I doubt he prepared at all, that is, other than snorting cocaine off a mirror in the back room before the show.
Tom
Parent
Re:Awww...c'mon guys.... (Score:5, Funny)
Parent
Re:Awww...c'mon guys.... (Score:5, Insightful)
For instance, the word "patent" is pronounced differently in the UK from North America. In the UK it is "pay-tent" and over here it's "pah-tent". That's just one example.
Point is [to paraphrase ballmer]:
Preperation (clap), preperation (clap), preperation (clap), preperation (clap), preperation (clap), [pitch of voice higher], preperation (clap), preperation (clap), [wheeze out of breath, pitch even higher], preperation (clap), preperation (clap), yeah!!!
Something tells me this sales guy will get neither punished nor lose their x-mas bonus. Some poor schmuck in engineering will take the fall for not making the demo "people ready".
Tom
Parent
Re:Awww...c'mon guys.... (Score:5, Funny)
One would be inclined to think that since you went and typed that word nine times, you would have managed to spell preparation correctly at least once...
Parent
Re:Awww...c'mon guys.... (Score:5, Funny)
[and I copy/pasted it. Yeah I know, I'm hardly literate. What you wanna fight about it?]
Tom
Parent
Re:Awww...c'mon guys.... (Score:5, Insightful)
Aw, c'mon; how many English dialects pronounce "mom" and "aunt" similarly?
Even to someone who's worked with voice recognition, that mistake simply isn't credible. If the software were anywhere near usable, it wouldn't confuse those words from anyone, especially not in a low-noise, no-echo demo.
This is a "No excuses" situation. That demo was simply a dismal failure due to some major bug(s).
Of course, the speech recognition field has a long history of staying in such a state forever. It's hard to find a product that, even with extensive training, doesn't produce howlers like this.
I did like the "killer" part
Parent
Re:Awww...c'mon guys.... (Score:5, Insightful)
Chances are he never even did a walk through of the presentation before the press was there.
Tom
Parent
Re:Awww...c'mon guys.... (Score:4, Interesting)
Try this:
Said: "How to recognize speech"
Understood: "How to wreck a nice beach"
No, it's not always easy to tell the difference...
Parent
Not the first MS demo embarrassment. (Score:4, Informative)
There, I found it. The file is an old QuickTime movie. I'm going to put this up on YouTube. There, that's done. Have at it [youtube.com].
Parent
Re:Awww...c'mon guys.... (Score:3, Interesting)
I'm not one to defend MS, but I speculate that the volume on his microphone was set too high, causing distortion and clipping. Look at the volume meter when he talks -- it goes all the way to the top.
Re:Oh Please (Score:5, Insightful)
Point is, if the sales guy had tried the system out beforehand he would have noticed it not working.
That is, suppose the code is total shit [I know, big stretch for MSFT]. Then isn't it likely it would have failed during the preparation stage? If you are saying "mom" and it always comes back "aunt" you may want to cancel the presentation.
That's why I think he didn't do any prep work for the presentation.
Tom
Parent
Since when did Mum sound anything like Aunt? (Score:5, Funny)
Since when did Mum sound anything like Aunt?
Parent
Hee hee (Score:5, Funny)
Re:Hee hee (Score:3, Interesting)
Voice recognition means permanent beta. Voice recognition only slightly improved during the last ten years. One reason is that the VR market it a trivial patent minefield. The rest is just performance.
Sure, we will get proper voice recognition some day. I would source it out to open source and integrate it back into my products once it will be ready.
Well (Score:4, Funny)
Re:Well (Score:5, Funny)
Parent
The Voice of Experience (Score:5, Insightful)
Experience is the human quality that enables you to recognize a mistake immediately when you make it again.
Dacap
So? (Score:5, Informative)
Win98 gone wild: http://www.youtube.com/watch?v=Hrbx9_AY720 [youtube.com]
Media Center Edition gone wild http://www.youtube.com/watch?v=j7EEbokKLHI [youtube.com]
We can add this one to the list too
Dear aunt (Score:5, Informative)
Final text:
Re:Dear aunt (Score:5, Informative)
http://blogs.msdn.com/robch/archive/2006/07/29/68
Parent
This sounds so much like Microsoft (Score:4, Insightful)
Yes bugs happen, yes vista is still in beta but rather then just admit "vista is still a buggy piece of crap software that can't even be used properly by its own engineers" they tell us to sit and wait because we can trust them to fix it.
To MS credit, it is a strategy that works.
Parent
Remember the Win98 BSOD? (Score:5, Funny)
http://www.ntk.net/media/developers.mpg [ntk.net]
Just from MicroSoft Insider (Score:4, Funny)
"Sir put down the chair, then we'll talk"
"No Steve wait up, don't do that"
"BOOM CRASH BOOM CRASH BOOM CRAASH WAAAH NOOO STOOOOP"
"DUDE, THE COMP HAS A BSOD! WAAH!"
It's hard (Score:4, Funny)
Vista couldn't differentiate between mom and aunt (Score:3, Funny)
OS/2 Still Kicking Microsoft's Ass (Score:5, Funny)
Speech recognition is still just a gimmick anyway. We still have a LONG way to go before it gets to the point that Joe Average User imagines it should be. Joe average user wants his computer to respond like the one in Star Trek. I still want to set up my Asterisk server with speech recognition, though, so that people can either dial or say the extension they want. It'd also be neat to pick up the phone, say "Call Mom" to the dial tone and have it call my aunt for me.
removing ambient noise (Score:5, Insightful)
why not just use two mics, one to record the ambient noise (positioned away from the voice mic) the other to record the voice (headset) then as you have two signals just subtract the ambient noise signal from the heaset signal , voila clean headset mic audio
works for music too, you could control your music player by voice even when its playing loud (at a party) by removing the music signal from the mic signal
-AJS
Re:removing ambient noise (Score:5, Informative)
What is done in practice and works extremely good, is modelling that "echo" as a filter (a FIR transversal filter, which is simply a delay line). You estimate the coefficients of the filter and use the music signal after the "room filter" has been applied to substract from the microphone signal. You then have the voice-only signal left.
This is setup is called AEC or Acoustic Noise Cancellation. It is used in every telephone and mobile phone there is and is crucial to ADSL. If an ADSL modem would not cancel out its own sent signal at its receiver, the attainable speed would be several times less. AEC is also the reason why talking immediately when you pick up a mobile phone leaves an audible echo of your own voice: estimating the coefficients of the filter is still taking place at that point.
See http://www.dspalgorithms.com/products/echo.html [dspalgorithms.com] for a diagram of the AEC or read Haykin's Adaptive Filter Theory if you're looking for a decent book on the subject.
Parent
Microsoft Innovation (Score:3, Insightful)
On MSNBC's front page - for about 30 minutes.... (Score:5, Informative)
I went to msnbc.com - and there it was, third on the list of videos on the main page.
I called this to the attention of two of my coworkers, and we viewed the video - total elapsed time, maybe twenty minutes.
Then I went to call it to the attention of a third coworker - and the video was no longer on the front page of MSNBC. OK, so maybe they've moved it off the front page, but it should still be on the Technology subsection, right?
Wrong.
Nor was it under Videos, nor anywhere else I could find it easily.
Perhaps this was just a normal rotation of a video. Perhaps not. But no matter what the real cause, there is the appearance that it was removed from the page because it was too embarrassing. Not good for Microsoft.
However, I will give MSNBC this - they didn't give Microsoft a free ride on this, they ribbed them pretty hard.
However, I knew that this would be appearing on other sources as a video that could be viewed outside of Windows. Actually, I am rather surprised that it took this long.
Now, as to the demonstration itself - it looks to me (a person who does signal processing and analysis for a living) like the presenter had the mike gain too high - every time he spoke he maxed out the bar graph on the display. *IF* he had the gain too high, and the audio was clipping significantly, that could make "mom" have enough of a pop to maybe sound like AUNT - especially if the software is using context to try to reduce the search-space for the words. Of course, that's why I would have a monitoring routine in the system, and if any of the samples are at 100% full scale, or if many of the samples are over 90% full scale, or the signal power is too high, I'd have my software adjust the mike gain down *and* flag an alert to the user. I'd also try to look for the mike element itself being overloaded.
Re:Is SR ever going to be good enough? (Score:5, Informative)
One thing it did do which was good though is tried to understand sections of speech, rather than just each word, which did improve accuracy. Words often follow patters and there are few words that make sense after a word, so it was often right with "over there".
SR tech will eventually be as good as on star trek as long as people work on it. I would give it 20 years if it is seen as something which could make a lot of money, 40 if you have to wait for interested people to do it for free on their own time
Parent
Re:Is SR ever going to be good enough? -- Yes! (Score:5, Informative)
I didn't believe it either, until I actually tried it. Dragon is the first worthwhile speech recognition solution I've seen that's practical for general use (Though I'd love if they'd release a "programmers" version to compliment the Medial/Legal versions). I get about 99% accuracy (a decent microphone is *very* important!)
Dragon 9 also doesn't "technically" need training, but accuracy further improves if you do bother to train it a bit. The NYT reviewer was able to get 99.6% accuracy after a short training session.
Here's a few reviews of version 9:
http://www.nytimes.com/2006/07/20/technology/20po
http://www.npr.org/templates/story/story.php?stor
Parent
Re:Is SR ever going to be good enough? (Score:4, Insightful)
Parent
Re:Is SR ever going to be good enough? (Score:4, Interesting)
They don't deserve credit for starting the "PC revolution". The credit properly belongs to the hundreds of little startups and hobbyists, the whole CP/M crowd and others like Amiga. Microsoft was a subcontractor to a giant monopoly (IBM) that stepped in after the little guys demoed there was a market, and took over that market. They succeeded mostly because of a marketing budget greater than the budgets of all the little companies combined.
And there's a good argument that, by marketing PC/DOS rather than CP/M, they set back the PC revolution by 5 to 10 years, the time it took for PC/DOS to match the capabilities of CP/M when IBM started their PC marketing campaign.
Sorry; that's the way "the Market" works in the computer field. Small, independent developers make something new and start selling it; the big companies then step in and take over the market through traditional monopoly strategies.
It's likely that we're now going to hear people crediting Microsoft for starting the "voice recognition" revolution by inventing the new idea that computers can understand speech. Marketing can redefine history like that.
(Whereas we computer geeks know that Al Gore invented speech recognition.
Parent
Re:Is SR ever going to be good enough? (Score:5, Insightful)
For example, how does the computer know that Picard wants to call Riker and isn't just talking about him? Oh and keep in mind the computer never misinterpreted something. In other examples, people would carry on intelligent conversations with the computer - all those holodeck scenes, Troi ordering chocolate, etc.
Star Trek-style of SR I think would be the holy grail and is probably always going to be out of reach. Barring some amazing breakthrough in AI algorithms, the computer power required just for the situations above would be incredible - and that's computer time that probably could be put to better use elsewhere, even if it was found to be possible.
I think the computer in the original Star Trek was more realistic - but even there the voice-recognition was far beyond what we're capable of today, as Microsoft has demonstrated so well. Plus all the blinkenlights that seemed to have no useful purpose were cool.
Parent
Re:Is SR ever going to be good enough? (Score:5, Funny)
Hmmm - holodeck, Troi, chocolate.....the combination of those three items is something that gives one pause to ponder.
Um, I'll be back in a little bit.
Parent
Re:Is SR ever going to be good enough? (Score:4, Interesting)
Well, maybe. But we invented microscopes around 300 years ago, and discovered microorganisms immediately thereafter. The understanding that some bacteria were involved in diseases followed quickly. But it was nearly 300 years before we successfully eradicated a disease (smallpox). Today, we're still battling new diseases, and we don't have anything like a general solution to all diseases. We have a few antibiotics that effect more than one disease, but we haven't made much progress in solving the problem of the development of resistance to our antibiotics. Hell, we can't even convince the general public that it's the evolutionary process at work here, and we've understood that for around 150 years.
I wouldn't predict any general solution to a complex problem like voice recognition in a mere 300 years. Maybe we will. But our history of general solutions to other complex biological problems is not encouraging. Neither is the history of our first 50 years of AI, despite the constant hype and Hollywood movies claiming that AI is just around the corner.
Parent
Re:Is SR ever going to be good enough? (Score:3, Insightful)
Probably. But it will have to get much better at using context. They're already using grammar as a cue, but it's going to take much more than that. Humans draw on memories of previous conversations, knowlege about the interests and mannerisms of the person speaking, and knowlege of the situation at hand. Even just knowing what's big in the news can help.
As for ambient noise, there's often
Re:are u serious? (Score:4, Insightful)
It's called modesty. If MSFT had any [and some humility] they wouldn't get laughed at so hard for this. I mean look at Linux. Find a bug in the Kernel, fix it, post notices that its. You don't see anyone saying "Oh hahaha, Linus is at it again!" That's because you also don't see Linus on CNN mocking the rest of the world.
Microsoft deserves all the negative press and humilitation they get because they are shameless, deceitful, greedy monopolistic bastards.
Tom
Parent
Re:are u serious? (Score:5, Insightful)
Hmmm, no. Maybe it's the way they deal with failures. Remember Bill gates trying hard to demonstrate the Media Center [google.com]? Some time after that Steve Jobs gave his regular Macworld keynote when his Mac didn't respond anymore. He moved a monitor switch to continue the presentation on another Mac and said: "Well, that's why we have backup systems here."
Parent
Re:Man, that brings back memories!!! (Score:4, Funny)
Parent
Re:Sequence of events (Score:5, Funny)
Parent
Re:That's REALLY sad... (Score:4, Interesting)
Parent