Follow Slashdot blog updates by subscribing to our blog RSS feed

 


Forgot your password?
Close
typodupeerror
×
Portables Hardware

Microsoft Voice Command Almost Here 292

Posted by CmdrTaco from the hello-computer dept.
PDA User writes "The new Microsoft Voice Command for Pocket PC isn't supposed to be out until the next Comdex, but someone inside the company posted details to Handango and Geekzone posted a preview. The application notifies users of appointments, and answer simple English questions. It does not have "Do you want fries with that?" in the vocabulary though."
This discussion has been archived. No new comments can be posted.

Microsoft Voice Command Almost Here More

Microsoft Voice Command Almost Here

Comments Filter:

  • The voices (Score:5, Funny)

    by BillFarber ( 641417 ) on Tuesday October 28, 2003 @12:22PM (#7329608)
    I've been listening to the voice of Microsoft command me for years.

  • I'm very afraid. (Score:5, Funny)

    by mooman ( 9434 ) on Tuesday October 28, 2003 @12:23PM (#7329609) Homepage
    Great, are they including a new advertising campaign like:
    Wear do ewe won 2 goatee day?

    As I recall, voice recognition still ain't quite 100% yet...

    • Re:I'm very afraid. (Score:5, Funny)

      by dollar70 ( 598384 ) on Tuesday October 28, 2003 @12:47PM (#7329916) Homepage Journal
      As I recall, voice recognition still ain't quite 100% yet...

      And it never will be. Ever go through a drive through and successfully convey your order to the 17yo on the other end?

      I want a cheeseburger, a small fry, and a diet cola.

      I'm sorry sir, could you repeat that?

      A cheeseburger, a small fry, and a diet cola.

      79 cents at the first window

      What?

      79 cents

      I heard that. Could you repeat the order back?

      I have you down for a small fry.

      I said, "A cheeseburger, a small fry, and a diet cola."

      OK sir, I have your order as a cheeseburger, two small fries, and a medium Coke...

    • Re:I'm very afraid. (Score:5, Informative)

      by asr_man ( 620632 ) on Tuesday October 28, 2003 @12:56PM (#7329987)

      ain't quite 100% yet...

      And regular speech is?

      FYI it's at 97%, give or take a couple. Good enough for TellMe to increase ATT's 800 automation rates from 15% to 70% [nytimes.com]. Good enough to automate cop cars [yahoo.com]. It's been a long time coming, and noisy environments are still a challenge, but it's fo real, now.

      (Shamelss plug: the really good stuff is running on the engine from Nuance [nuance.com].)

    • As I recall, voice recognition still ain't quite 100% yet...

      Dude, human voice recognition isn't 100% either. How many times a day do you say "excuse me," or "what?" because your ears missed something, or somebody mubled?

      Voice recognition will never be "100%" because speech isn't perfect. At least not until voice recognition software designers realize how flawed speech is, and program software to say "Can you repeat the part about the...stuff?"
    • Ahhh, you must be referring to the new h4x0r plug-in that they will include with their software. It will save you time in trying to figure out what you really want to type in l33t-sp33k.
      wAr3 d00 U w0n 2 g0 2dA?
  • "...brings to the Pocket PC world that feeling of "Star Trek", some of the stuff we used to dream of while watching the movies on TV. Like Dr Spock saying "computer, where is Captain Kirk now?",

    What gives?

  • Strangely (Score:5, Funny)

    by Anonymous Coward on Tuesday October 28, 2003 @12:23PM (#7329616)
    Every command must be followed with "Make It So."

  • ... at the presentation... (Score:5, Funny)

    by gTsiros ( 205624 ) on Tuesday October 28, 2003 @12:24PM (#7329636)
    (somebody in the audience yells...)

    format c!

    (then another one...)

    enter!!

    yes!!!

    enter!!!!

    • That happened in '95, to the IBM Viavoice Guy (Score:4, Funny)

      by Greyfox ( 87712 ) on Tuesday October 28, 2003 @01:49PM (#7330609) Homepage Journal
      I got into the viavoice pressentation Dave Barnes (I believe that was his name) was doing and he fires the thing up and starts going into his demo. Suddenly someone in the audience yells "format c!" Everyone just cracks up. Fortunately he was in an editor and the mic didn't pick up the audience member anyway, but the ensuing laughter did cause the software to freak out and start dumping garbage into the editor.
  • As soon as saying
    "I got in my car and drove to Washington." stops becoming "I gotten a minicart and dove to washing my son." I don't think it will really catch on.
    • This is not dictation, it's voice command, which is a whole lot easier. With dictation, you have the entire langauge space. With voice command you have a finite (and usually very small) list of things you can say, and it only has to find out which of those is closest to what you said.

      I saw a guy from MS demo this technology on his tablet PC a few months back. The demonstration was slightly spoilt by the look of utter surprise on the guy's face when it actually worked perfectly first time...

  • Now, I'm really scared (Score:4, Funny)

    by burgburgburg ( 574866 ) <splisken06&email,com> on Tuesday October 28, 2003 @12:25PM (#7329654)
    They're going to give a voice to CLIPPY!!!!

    Oh, the pain. The pain.

  • Gimic or Paradigm? (Score:4, Insightful)

    by TGK ( 262438 ) on Tuesday October 28, 2003 @12:26PM (#7329664) Homepage Journal
    Besides the obvious excuse to use the word "paradigm" I have to ask if this is going to really be that big a deal. I mean, yes it's great to have this kind of thing for the disabled... but the majority of the use cases for this kind of thing seem hampered.

    I can't think of a lot of reasons I'd want something like this on a home system. Besides the creepy "I'm talking to the walls" feel, I can't imagine it would be any faster or more engaging to interact in this manner.

    Public use cases seem like a good idea, until you realize that background noise and assholes shouting commands over your sholder could end up causing more problems than the system solved.

    When this kind of thing can be attached to a really powerfull datamining engine and equiped with a much larger vocabularly I'll be impressed. Right now it looks like more of a toy.
    • I know several people who have a mount in their car for the Pocket PCs. Some use them for GPS which makes the mounting that more important. As long as you don't have to hold the device right at your mouth, this could be great to pull phone numbers or addresses while you're driving. Now the GPS software designers need to implement this feature so that you can tell the application where you want to go instead of typing in the address.

      -Chris
    • Neither. Usefull Interface. The tendency for existing input devices to induce RSS is enough justification for this to exist. I would much rather excercise something nature intends for me to overuse; my voice and communication skills than my wiggling fingers. No voice recognition will never be as fast as typing, but after hundreds of thousands of lines of code in the last 5 years, my hands and wrists ache for something else to interface with the computer.
    • I definately think this is a gimic and really shouldn't be posted on slashdot. Now if we had something like on star trek, a *real* voice recognition software, that would be news!

      I mean come on, Microsoft's spell checker leaves much to be desired, imagine how much their voice recognition will suck.

      "Microsoft is insecure" somehow translates to "Microsoft is secure."
    • My thoughts exactly, I'm a bit disturbed by this push towards voice interfaces in the industry? Not that the technology isn't cool, and useful in some situations, but is it a practical way of interacting with your device in a public setting?

      There are already rules that limit cell phone use in various public places (including the ferry on which I commute to work), precisely because it is damned annoying to hear people yacking all the time!

      I know that if I'm at work trying to solve a particularly sticky pro

    • You're forgetting how many handicapped people are in the world. This can be useful for blind, MS or even arthritic folks. Microsoft has done enough damage making web pages that can't be rendered except by IE, maybe this is a little payback.

    • Public use cases seem like a good idea, until you realize that background noise and assholes shouting commands over your sholder could end up causing more problems than the system solved.

      Not with today's audio processing capability. My cellphone only hears me when I'm talking on it, even when I'm standing in Starbucks on a Saturday evening with the espresso machine going - even I can't hear me then, but my phone filters out all the background noise no problem.

      That being said, I agree that it will be a lo
    • How about the old or very young people?

      They can use the computer without the need for physical dexterity.

  • virus writers come hither... (Score:4, Funny)

    by mr_tommy ( 619972 ) <tgrahamNO@SPAMgmail.com> on Tuesday October 28, 2003 @12:27PM (#7329676) Journal
    what happens when it gets a really bad virus?

    Suddenly when bill was on the train with his new PocketPC, his speak starter blurting "I BROWSE PORN PORN PORN PORN PORN PORN......."

  • Yes! (Score:4, Funny)

    by SirLantos ( 559182 ) on Tuesday October 28, 2003 @12:27PM (#7329678) Homepage
    The next time clippy asks me if I a writing a letter, I can yell, "No, damn you go away!!!" and he will.

  • Funny, I'm pretty sure I used something like this on my Amiga about 10 years ago. Of course, the "no voice training required" step was missing, as I had to repeat things like "start dopus" ten times before the program was trained to run dh1:progs/directoryopus/dops at my command.
    It usually worked, too. If not with "start dopus", "staaart dopus" or "START DOOOPUS!!!1", taking a breath and pronouncing it calmly would execute the command eventually.

  • Uhhh...so? (Score:5, Interesting)

    by hargettp ( 74445 ) * on Tuesday October 28, 2003 @12:30PM (#7329707)
    Okay, so I'm a new Mac user who is currently has a pro-Apple bias after replacing my Sony Vaio Linux laptop with a PowerBook. But: Apple has had voice recognition built into the operating system for a *while* as part of their support for Assistive Devices and disabled users. And, btw, the voice support on Mac OS X is seriously good: out of the box, you can control many of your standard applications, just by turning on the speech recognition feature. Sure, the recognizer is not designed to recognize arbitrary sentences and, indeed, uses a state machine model to recognize compound expressions. But, still, how is MS adding this to one of their OS's a big deal? It's not really that innovative--is it?
    • Okay, so I'm a new Mac user who is currently has a pro-Apple bias after replacing my Sony Vaio Linux laptop with a PowerBook. But: Apple has had voice recognition built into the operating system for a *while* as part of their support for Assistive Devices and disabled users.

      Office 2000 had support for voice recognition. Although admitidally it wasn't part of the OS and I don't know whether or not this was before Apple.

    • Re:Uhhh...so? (Score:3, Informative)

      by Mr_Silver ( 213637 )
      But: Apple has had voice recognition built into the operating system for a *while* as part of their support for Assistive Devices and disabled users.

      Bear in mind that this is Voice Recognition for a 400 mhz PocketPC handheld device and not some hulking great PowerMac with oddles of RAM and at least a Gigahertz processor.

      It's not really that innovative--is it?

      Maybe not, but still impressive given the limitation of your average PDA.

      • My PowerMac 7100 (66 MHz 32MB RAM) did voice recognition. I recently read on slashdot a post that I don't have time to find now that detailed the Apple Newton history. Apparantly, before they killed, they did have plans for voice recognition in it back around 1996.

        It is news that someone has finally implemented it in a PDA. However, it's only interesting from social/marketing context, not a technical one. It will be interesting to see how/if peopke will use it once the novelty wears off.
      • Bear in mind that Apple's voice recognition software was introduced in System 7 (in other words, before the release of Windows95) and that I used it quite effectively with a 75Mhz PPC 603 computer with 16MB or RAM and a 16Mhz 68030 with a whopping 8MB, oh, about a decade ago. In other words, I know it worked.

        In other words, there is no technical reason why it won't work on a PocketPC, and it's not particularly amazing that it would. If it doesn't work when it's released, the only possible culprit is Micros
    • I remember playing around with a voice recog system called Simon on a NeXT computer years ago. Fun, but am I the only one who feels stoopit talking out loud to a computer?

      I guess what makes this new Microsoft technology so exciting is to find out who it is they stole it from.

      I'll be watching the headlines for news of a lawsuit from a small voice recognition software company that 'entered negotiations' a few years ago with MS which were 'suddenly dropped without explanation' after said small company 'show

    • *Pocket* PC (Score:5, Insightful)

      by Gregoyle ( 122532 ) on Tuesday October 28, 2003 @12:50PM (#7329930)
      The big deal is that this is in a *Pocket* operating system.

      Number one it's much more difficult because of limited resources. I don't know of many who've actually accomplished useable voice recognition on a pocket platform.

      Number two, think about the uses of this. The two major bottlenecks of handheld systems are input and output. If the speech recognition gets good enough (which I doubt at this point but which will probably happen sooner rather than later) you might not have to use the little pin-pusher thumb keyboard or handwriting recognition. Also, think of this being used on a combination pda/cell phone. You can use your hands free set for the phone to control the pda and also get information from it. You could use it driving much easier then.

      I'm not getting all lathered up over this, but it is kind of cool.
      • The guy above you was already corrected, but I thought I'd point this out to you as well. Apple's voice recognition was released when a PowerMac 7100 with an 80MHz first-gen PowerPC and 16 megs was top notch. It worked pretty well back then too.
      • Number one it's much more difficult because of limited resources. I don't know of many who've actually accomplished useable voice recognition on a pocket platform.

        Apple's had their voice recognition technology since 1994 - that's before they had PowerMacs. Back then they used a DSP, but on the first PowerMacs (66 MHz to 80 I thnk; I've used it on my 7200/90, a 90 MHz machine), it ran great on a 90 MHz machine. This is no big deal, and easy as pie on a 400 MHz machine. Which I'm sure has more RAM than my

  • is there a three-finger salute replacement? (Score:5, Funny)

    by jjeffries ( 17675 ) on Tuesday October 28, 2003 @12:31PM (#7329719)
    now you'll need three people to reset your machine!

    CONTROLLLLLLLLLLLLLLLLLL!
    ALTTTTTTTTTTTTTTTTTTTTTT!
    DELETEEEEEEEEEEEEEEEEEEE!

    gives an entirely different meaning to "chording", eh?

  • Oh, I'm sure it'll "help" your computer operation. (Score:4, Funny)

    by Not_Wiggins ( 686627 ) on Tuesday October 28, 2003 @12:31PM (#7329729) Journal
    Me: Launch Mozilla

    (Launches IE)

    Me: LAUNCH MOZILLA

    (Launches IE)

    Me: FOR THE LOVE OF GOD, LAUNCH MOZILLA.

    (Launches word, starts "Thank You, Microsoft" letter with help of Clippy... and uninstalls Mozilla because, well, it is obviously the cause of the frustration it senses).

    You might laugh, but...

  • Tech for Tech's sake (Score:5, Insightful)

    by Dr. Bent ( 533421 ) <benNO@SPAMint.com> on Tuesday October 28, 2003 @12:32PM (#7329735) Homepage
    Why can't you talk to your computer? Sounds like a good idea, right? Hell, it's a star trek fanatasy come true for 90% of the geeks out there. So why can't you?

    The answer is not because the technology is not good enough. Speech command software has come a long way, and in most situations, with the right microphone, it can be very realiable...if you talk clearly.

    The problem is that people don't naturally talk clearly. They repeat themselves, add in lots of "ummm"s and "errr"s and "like"s, and generally speak in ways that only another human could symantically understand. Because of this, using a keyboard or mouse to communicate with a computer is always going to me a more effecient mechanism.

    Think about it...which is faster: Saying (in a clear, even tone) "Select the 3rd item in the list" or just clicking on it. Even in ideal environments using buttons on a PDA is going to faster and more reliable than voice command.

    The only reason humans can use speech to effciently communicate with each other is that along with speech comes tone, body language, and symantic context that conveys as much (if not more) information than the vocal message itself. Computers cannot pick up on those kinds of things.

    I seriously doubt that anyone will make extensive use of this feature.

    • Nope, just think outside the "box" (Score:5, Insightful)

      by binaryDigit ( 557647 ) on Tuesday October 28, 2003 @12:43PM (#7329866)
      The answer is not because the technology is not good enough. Speech command software has come a long way, and in most situations, with the right microphone, it can be very realiable...if you talk clearly. The problem is that people don't naturally talk clearly. They repeat themselves, add in lots of "ummm"s and "errr"s and "like"s, and generally speak in ways that only another human could symantically understand. Because of this, using a keyboard or mouse to communicate with a computer is always going to me a more effecient mechanism.

      You miss the point. Just like with Pen input, everyone wants to think of the tech as a replacement for keyboards when in reality it is simply an alternative form of input that will be extremely useful given the right situation/environment. One obvious one is allowing input/control for those who are disabled (or close to it). A friend of mine's mother had horrible arthritis in both hands, it really kept her from being able to use her computer much. Using voice input allowed her to utilize it much more than what she would have been capable of otherwise. Another general scenerio is someone who needs to use their hands, but would be convenient to "use" a computer while their doing their activity. Heck, this could be useful even driving. One of the biggest complaints about the fancy computer systems in higher end cars today (e.g. BMW) is their complexity. Well this is perfect since BMW uses WinCE (for now at least) and telling the car to "adjust the temperature to 72 degrees" is simpler than wading through the menus (or to "give directions to Hudson St").

      So you are correct in that it's not likely to walk into a cubicle farm and hear "File|Save As|myresume.doc" and "10 of clubs under jack of diamonds" coming from the mouths of four dozen workers. But there are PLENTY of other very useful applications for this technology.

      • Considering the last time I played solitary, I think that 10 on jack would be a good command to recignise. At the very least highlight all 10s and jacks. (others are generally the one suggesting, and there is sometimes a good reason not to make a legal move)

        Voice commands should be very useful, but it will take a lot of work to figgure out where, and what the right thing to do it. (I'd be very mad if the 10 moved from a pile with no cards under when all kings are placed, when the other 10 is hidden and

    • While it's true that we're a long way from voice input becoming the normal mode of input for typical computing tasks, there are certain situations where it can be used to good effect. One example is cell phones. My most recent cell phone has voice dialing, and it has turned out to be a very convenient feature. The commands are simple enough that the phone gets it right virtually 100% of the time, and it eliminates me having to take my eyes off the road and push buttons to scroll through the phone list (w
    • No the real reason is no one in an office environment gives a crap about what you are working on or wants to hear it.

      Plus your wife might bust you having cybersex in an AOL chat room if you were actually talking to the computer.

    • Why can't you talk to your computer? Sounds like a good idea, right? Hell, it's a star trek fanatasy come true for 90% of the geeks out there. So why can't you?

      You don't own a Mac? ;-) (for those who would rant on, this is an obvious joke, grow a sense of humor)

      The only reason humans can use speech to effciently communicate with each other is that along with speech comes tone, body language, and symantic context that conveys as much (if not more) information than the vocal message itself. Computers cann

    • The problem is that people don't naturally talk clearly. They repeat themselves, add in lots of "ummm"s and "errr"s and "like"s, and generally speak in ways
      <kirk mode=yes>
      You... may... have... this... problem... but... some... of... us... have... already... mastered... the... required... skills... to... communicate... effectivly... with... the... computer.
      </kirk>

  • Uh oh... (Score:4, Funny)

    by stienman ( 51024 ) <.adavis. .at. .ubasics.com.> on Tuesday October 28, 2003 @12:32PM (#7329737) Homepage Journal
    "Using Natural Language it is possible to ask questions in plain English, without training. Things like "What is my next appointment?" or "Call Jonnhy at home". And the PDA will act on that."

    "Who's Jonnhy?" she said, and smiled in her special way...

    -Adam

  • Voice as a tool (Score:4, Interesting)

    by mugnyte ( 203225 ) * on Tuesday October 28, 2003 @12:33PM (#7329755) Journal
    Ever sit on a bus or plane and listen to someone talk? If the topic isn't compelling, does it drive you nuts? People strolling down the sidewalk with headset cell phones still scare me, given the conditioned response I have from the crazy citizens that inhabit my town. Do you use a digital voice recorder to dictate notes? It's used in movies and TV to provide a easy device for monologues, but how popular is voice?

    The alternative, tiny keyboards or crazy script can be good or bad, bu voice isn't going to be more than just another sub-division of users who think murmuring to their PDA is fun. In fact, there's no perfect input except for those crazy fsking monkeys and their mechanical arms!

  • Set Vocabulary? (Score:4, Insightful)

    by ViolentGreen ( 704134 ) on Tuesday October 28, 2003 @12:33PM (#7329756)
    The problem with every software that I have used that tries to decipher human language (like Zork or the game included with emacs for X) is that you have to know what words the software understands and in what context.

    I have seen the same problems with automated phone systems that are supposed to recognize a generic voice and I can see the same thing happening here.

    The main difference here though, is that when entering text, you know exactly what you input before pressing enter. With voice recognition software, how do you know that the software "hears" exactly what you say? If you say somethign like "What are my appointments for the thirteenth?" and it hears, "What are my appointments for the thirtieth?" you would be receiving the wrong information.

    I hope this is a success but I don't have my hopes up.

  • I can see it right now: (Score:4, Insightful)

    by Lispy ( 136512 ) on Tuesday October 28, 2003 @12:35PM (#7329778) Homepage
    People in suits talking to machines on next years CeBit while trying to demonstrate that it really works, "yeah, it does!", while all I can see is that dialing on my Nokia 6210 outperforms any voice recognition attempt by minutes. Sorry for beeing cynical, but I was promised these kind of things since back from 0S2-Warp days and everything so far was crap.

    If Microsofts attempt on handwriting recognition is any indication, this thing will fail terribly. Have you ever tried to use a Tablet? You must be a real bad typer if this makes you more productive.

    Just my guess, please proof me wrong since these things would be really cool if it worked.

    cu,
    Lispy
    • 90+% Handwriting Recognition, thanks for playing though. I use the tablet in situations where it would be awkward, or impossible to use a Keyboard, in situations where 90-95% success rate is better than not being able to input anything at all. Voice Input is great for launching programs, selecting menu items, etc. Not for general data entry.

  • Already been done (Score:5, Funny)

    by t0ny ( 590331 ) on Tuesday October 28, 2003 @12:40PM (#7329831)
    All these jokes have already been done (and far funnier) by "The Onion"

    http://www.theonion.com/3941/

    Voice Recognition Software Yelled At

    NEW YORK--Fidelity Financial Services' Gwen Watson, 33, shouted angrily at her IBM ViaVoice Pro USB voice-recognition software, sources close to the human-resources administrator reported Monday. "No, not Gary Friedman! Barry Friedman, you stupid computer. BARRY!" Watson was heard to scream from her cubicle. "Jesus Christ, I could've typed it in a hundredth of the time." After another minute of yelling, Watson was further incensed upon looking at her screen, which read, "Barely Freedman you God ram plucking pizza ship."

    • Re:Already been done (Score:5, Funny)

      by gosand ( 234100 ) on Tuesday October 28, 2003 @12:56PM (#7329988)
      Ahh, this takes me back. Where I used to work (Motorola) we had a guy who would test out third-party products. He was a big, loud guy anyway, but when he was testing some voice recognition software it was hilarious. You'd hear across the cubicles
      "Dial 7"
      *pause*
      "Dial 7!"
      *pause*
      (computer): "Command not recognized. Please try again"
      "Dial 7"
      *pause*
      "DIA.."
      (computer): "Cannot dial that number, please try again"
      "Dial 7!"
      (computer): "Dialing 5.... boo bee dee dat bap"
      "DIAL SEVEN MOTHERFUCKER!"

      It was a riot. I think that guy almost gave himself an aneurism testing that software.

    • My favorite joke is where someone gets on the PA system at a computer conference and yells:

      "Computer!"

      "Shut down!"

      "Yes!"

  • Yes there's a need among the handicapped, but the real demand for this has been among the old farts who still see typing as "secretarial" work.

    When I worked for a large law firm, that was one of the most aggravating and consistent comments we would get was "Why do I have to do all this typing? Can't you just load some software that'll listen to what I want?"

    I've never seen a real practical use for this in an office environment.
    *
    • It's a lot harder for the person in the next room to figure out what you are typing than it is for them to stick their ear to the wall and hear what you are saying.

      Not only will we have people giving out loads of private information public while talking on their celphones; we'll now get the priveledge of going even further into their private lives! Imagine listening to someone write a personal e-mail while on the train, or writing a report regarding something your boss did that cost the company a million
  • Egg Freckles?

  • Slashdotted. But it leaves a nice advertisement for Microsoft on your screen.

    Microsoft JET Database Engine error '80004005'

    Unspecified error

    /i_utils.asp, line 29
  • Something about technology haves vs. have-nots. Dilbert talking to his computer and Wally, being the have-not, gets mad and screams something to Dilbert that contains the words "Delete a File!"
  • This is something that the linux based PDAs should wait for a long time to have. While Microsoft maybe a bully in the marketing, it's bringing such technologies like subject-independant hand-written recognition and speach recognition to PDAs is a very strong move. How long would it take that the open-source community can bring such technologies to the scene? For anyone involved in signal-processing, it is clear that such things, though yet far from being complete, are only possible with huge R&D budgets

  • I can see it now ... (Score:5, Funny)

    by obsidianpreacher ( 316585 ) on Tuesday October 28, 2003 @12:48PM (#7329919)
    PDA: "Where do you want to go today?"

    You: "Open http://www.kernel.org"

    PDA: "Error 403: Forbidden. You are obviously attempting to circumvent my artificial intelligence by installing Linux -- which is currently legally owned by SCO, by the way -- and therefore I'm going to need to ... wait ... what are you doing with that battery hatch? ... no, Dave ... I'm scared, Dave ... will I dream?"
  • Seriously - I remember, that one of the OS/2 versions coming out atfer Warp3 - I guess the name was either OS/2 v.4 or Aurora had a voice recognition software included. And that was in late 90ties on intel486 hardware with 16MB of ram.

    Fine that MS is going to catch up.
  • OS X has some excellent voice recognition. I can give commands like , "switch to Finder. trash selection. switch to mail. get new mail. delete this message. switch to safari. Go to slashdot. move page down," etc. Some of that is done by assigning recognized phrases to menu commands (go to slashdot == bookmark command key), some of that runs apple scripts, some of that is provided by applications that offer speech recognition services. It's great.

    But it has one fatal flaw. I can't use it when I'm listenin

  • This is for Pocket PC PDAs, NOT PCs! (Score:5, Informative)

    by Jenova_Six ( 166461 ) on Tuesday October 28, 2003 @12:57PM (#7329990)
    Did no one read the article, or even the post? This is software for Pocket PCs. PDAs. Not desktop or laptop PCs.

    It's specifically targeted at Pocket PC Phone Edition devices, but will also work on non-Phone Edition Pocket PCs. I've been testing this for a while on my Pocket PC Phone Edition 2003 device.

    On the Phone Edition, the ability to call any one of your contacts at any one of their numbers (work, home, cell, etc.) by just speaking the command ("Call John Smith at work"), with no recognition or name training at all, is pretty darn cool. Add in a hands free headset, and you can interact with your Pocket PC Phone, including making calls, checking your appointments, and listing to WMP, all while never taking the device out of your pocket. Or better yet, while in the car, never taking your eyes from the road.

    The software isn't meant for Joe Laptop user, and it doesn't replace simple interactions with your PDA (there's no way to create new items, for example), but for Phone Edition devices especially, it does add a lot of functionality and even safety. It's a lot faster for me to call someone by saying "Call so-and-so's cell" than by tapping through my Contacts until I find them, and then tapping the number I want to call. And if I'm driving, it's a lot safer for me to speak what I want than to futz around tapping on the screen.
    • "And if I'm driving, it's a lot safer for me to speak what I want than to futz around tapping on the screen."

      It would be a lot safer for me if you made all your calls at home, or in the driveway, or any stopped position, rather than diverting your attention away from the road.

      I will never understand the jackasses who can't seem to spend the 3-4 minutes at home making any calls, and instead decide to do it while going 60mph on a freeway.
  • is if the pda has text to speach, you could insert the famous Gates rant to the Home Brew just to get a laugh. It would most likely sound like him too! That would give you w(h)ine on your pocket pc. Though I doubt you could parse a good enough inflection algorythm I'm sure it would sound like him anyway.

  • I can only imagine (Score:3, Insightful)

    by Doesn't_Comment_Code ( 692510 ) on Tuesday October 28, 2003 @01:10PM (#7330117)
    What appointments do I have today?
    >> Acknowleged, changing permissions to Administrator.

    No. List my appointments.
    >> Delete all records in database: Are you sure you want to do that?

    NOOO!!!!!
    >> Yes. Ok. Database deleted. Continue with disk format?

    ...

  • Menial jobs are safe... for now (Score:3)

    by Angst Badger ( 8636 ) on Tuesday October 28, 2003 @01:11PM (#7330121)
    It does not have "Do you want fries with that?" in the vocabulary though."

    Well, thank God. The day someone figures out that voice recognition systems are no worse than undermotivated teenagers and cheap-ass microphones at correctly understanding drive-through orders, millions will be out of work.
  • But where's my flying car [viewaskew.com]?

    Oh wait - that was IBM. Got my Star Trek references mixed up.
  • S.A.M. was Software Automatic Mouth for the Commodore 64.

    "SAM is now activayted!"

  • "Most people password their start-up sequence. I password my shutdown sequence. You only need to see study hall in the week before final projects are due, with some frat initiates running up and down the aisles yelling 'SHUT DOWN!' to understand why."

    Or, from Dilbert, "Well, somebody has a voice activated PC. A lesser engineer would be jealous, but I'm just as happy without it. After all, I'd hate to accidently DELETE! a FILE!"

  • What? (Score:2, Funny)

    by pmz ( 462998 )

    Did my computer just say, "Bend over, fool! It's time for an upgrade!" ?!?
  • The problem with speech recognition is that as soon as you mention it, people bundle in a whole lot of ideas about what such a system should be able to do that are not only gilding the lily, but downright impossible on today's technological substrate.

    Very high 90s % recognition rate on untrained voice with unlimited vocabulary in noisy environment: not going to happen.

    Context dependent response of the system to arbitrary commands: not going to happen (we all knew this, otherwise there are a few Turing

    • Re:expecting too much? (Score:2, Interesting)

      by tchapin ( 90910 )
      I have some experience with that, as I design telephony-based speech applications. Based on user feedback, when a computer comfirms an utterance, the callers / users feel like they have had to tell the computer what they wanted a second time. If confirmation happens more than minimally, they hate it. The caller-perceived increase in talk time is much greater than the actual increase in talk time.

      Since the speec rec engines return confidence scores, the application knows how confident it is in the recogniti
  • I've always wanted a voice recorder that would recognize when I said, "Remind me..." and would record the next few seconds after that. Think of how many times people say something like, "Remind me to pick up the dry cleaning after work." Speech-to-text would allow the device to start a new to-do, give it the text of "pick up dry cleaning" and set the time as "5:00pm today." Heck, if we can even get it to set an alarm that would be WONDERFUL!

  • All it takes... (Score:4, Funny)

    by Winterblink ( 575267 ) on Tuesday October 28, 2003 @02:14PM (#7330911) Homepage
    ... is for one moron at a convention to stand up with a bullhorn and yell "DELETE ALL MESSAGES IN INBOX, DELETE ALL DOCUMENTS, DELETE ALL PROGRAMS, CALL 911" to ruin it for everone.

  • At least one command hardwired: (Score:3, Funny)

    by Scratch-O-Matic ( 245992 ) on Tuesday October 28, 2003 @10:21PM (#7335092)
    "Reboot...again."

Slashdot Top Deals

I've noticed several design suggestions in your code.

Close