Follow Slashdot blog updates by subscribing to our blog RSS feed

 


Forgot your password?
Close
typodupeerror
×
Linux Software

Linux PDA w/Voice Recognition 69

Posted by CmdrTaco from the ain't-that-interesting dept.
Hotaine writes "Lernout & Hauspie is working on a Linux PDA with speech regognition built-in. " It can do things like read (and record) emails, find weather, do stock quotes or whatever. Of course, you can't go out and simply buy the vaporware yet, but it has potential.
This discussion has been archived. No new comments can be posted.

Linux PDA w/Voice Recognition More

Linux PDA w/Voice Recognition

Comments Filter:
  • And The Wizardry Compiled, I think.

    Great books, anyhow. Rick Cook also writes relatively clueful tech articles...
    ---
    pb Reply or e-mail; don't vaguely moderate [152.7.41.11].
  • According to thier site, they did a live demonstration of some of this back in early feb on CNN. Anyone see it? Does it really work?

    And more importantly, I want to know if anyone knows if there are screenshots.

    -Brent
  • It has been out for a long long time now.
    My first voice recognition system was Voice Master for the Commodore 64.

    I'm sure there is a long list of systems that allready has this feature.
    However I'd like to see Linux on that list. A project exists to do just that but I'm unimpressed with the results so far
  • Which means that Bill will wait for them to make something cool and then make a half-baked port of it to Windows ;)


    Ehm... L&H already does cool stuff on Windows :-) What we did now was port it to Linux...

  • According to thier site, they did a live demonstration of some of this back in early feb on CNN. Anyone see it? Does it really work? Better yet, is there an opensource, freely available Linux for PDA's out there that may also be doing something similar?

  • How does one design an electric motor? Would you attach a bathtub to it, simply because one was available? Would a bouquet of flowers help? A heap of rocks? No, you would use just those elements necessary to its purpose and make it no larger than needed-- and you would incorporate safety factors. Function controls design.

    --Robert A. Heinlein
  • Come on, Commander! The original date is in the freaking URL -- Feb 8,2000. Do you really think that the slashdot submitters would have *missed* this story two months ago? No. They didn't. You already posted it.

    disappointed, and waiting to get moderated down :(.

  • Cool! Why not wait to do a Press Release and fake demo on this until half an hour after the next MSFT vapourware announcement about WinCE?

    Who needs ethics when we can just get down in the mud with Bill...

    And, while we're at it, why not get rid of this whole Open Source concept for this Linux PDA - it's not like we're any different than the old guard ...

  • I have taken a look at the prototype at CeBIT 2000. It was, they said, based on an intel strongarm processor, but they are desperately looking for some hardware company to develop the thing. The PDA they had at the booth was a dummy - unable to perform anything.
    Isdaron
  • On the screen is a talking head

    Why have a talking head on screen? Thats about as useful as the dancing paperclip in everyones favorite office suite. If thats all you are going to do with the screen, why just not have a screen. I suppose the screen could be used for displaying data, but please, no talking heads when there is no data to display.

    Spyky
  • I dont want screen shots I want Sound Shots.

    Cat whey eye cain evil hugh eat hit eats trance later.

  • The article is from 2/7/2000. I saw this news a long time ago. Are things so slow /. needs to dredge up stuff nearly 2 months old as filler?

  • You're using your Palm and suddenly somebody yells from across the room "C-D slash enter R-M space dash F-R enter"? Hope you're not root :-)
  • hey, not a bad idea.. Sounds like a cross of a keyboard and sound card.
    A microphone device that can translate your voice to text, and it outputs text into where you plug your keyboard in.
    OS independant, usable most anywhere a keyboard can be used. Boy would it fool typing tutors, and alt-ctrl-delete is no longer a three finger salute but .. hopefully you can bind words to key combinations..
    bind "reset" to alt-ctrl-delete, instead of saying "hold alt hold ctrl hold delete release" or something as silly..
  • This concept is in development through a project at Stanford. The "Total Access Port" (TAP) allows one to use whatever UI they prefer (voice, eye track, chordic keyboard, etc) for any device. The user portion of the device translates their input into UI commands which are interpreted through the TAP port on a device, such as a computer, ATM, microwave, etc. It's primarily designed for the disabled, but holds promise for wider application as well. See Archimedes Tap Project [stanford.edu] for more details.

  • I found three on The Very Big Online Bookstore [amazon.com] and found the fourth on Abebooks [abe.com]. They are (maybe in order) The Wizardry Consulted, The Wizardry Cursed, The Wizardry Quested and The Wizard's Bane by Rick Cook. Fun stuff; and this PDA brings us on step closer to making SF^H^H fantasy a reality...

  • I know this is offtopic but it needs to be said. I'm so tired of these companies calling every product a 'solution', like we who don't have it all have problems. This article was so thick with marketing jizz i could barely tell what they were describing. Was it a "mobile platform solution for corporate users with mult-cross-world-any-phone support" with "product solutions again?" Why the hell can't they just say they have a nifty PDA that can use speech recognition, even on the go, through a telephone, etc. and it runs linux.

    The rest of that was just crap.
  • Yea, but do you know his password?
  • They seem to be all about advances for linux, yet they are using active server pages. Ahh the industry is interesting like that. --jay
  • I think we can all agree that voice recognition is still in the somewhat early stage, meaning that you may have to adapt your voice to get the thing to work correctly. We could also probably agree that handwriting recognition isn't perfect, you have to adapt your handwriting to get the thing to work correctly. Similar eh?
    --------
    ...hit my head on the wall of the jail where the two of us live today. - TMBG
  • PDA with a wireless modem that can talk. And I will try to be one of those h8x0r d00z and dial up 555-wopr with my PDA, in the park, away from FBI, and have it tell me... Shall we play a game? No longer am I bound by haveing to punch in the cordnates of Redmond or any other evil places, I just yell...Nuke the heck out of billy boy...

    Hmm...

    Or better yet... Now with my PDA I can be like James Bond, and tell my PDA and my new car with three legged robot where to go while shooting my nerf gun at evil borg's in my back seat...and then I can get apache for PDA and stream it over the internet..

    hmm....oh well.
  • BTW...Linuxhaven.com got updated... I fixed it...and had to reset the messages.
  • ...but can I get a copy of their speech recognition software for my computer (free would be even better, and open-source, especially for a product from "the professionals", would be super-cool)?

  • Monotonic computer voice:

    BASH Apt COMMAND NOT FOUND
    BASH Hem COMMAND NOT FOUND
    BASH A-HEM COMMAND NOT FOUND
    BASH ! EVENT NOT FOUND
    EXECUTING COMMAND DAMN
    UNABLE TO DAMN WIRELESS MODEMS.

    OOPS - Debian not found. S**t.

  • Apt-get update.

    Ahem... APT-GET update.

    A-HEM! APT-GET UPDATE!!!

    Damn wireless modems.
  • Did you ever read the Wizardry series? The first two books are bundled as The Wiz Biz. Really entertaining series. Well, the programmer develops a computer system with magic (makes sense in context, hard to explain) with a verbal interface. He calls out to the Emacs from which he does everything...

    Alex
  • It is. For one, these voice to text systems use "close" microphoes. I chatted to some guy from Dragon Systems about it, and even had a go at trying to get his microphone to pick up something that I said, and they just doesn't work like that.
    Thad
  • Why post it if you cannot buy it? Sure *I* can come up with briliant ideas.....and not have anything to show for it..... lame
  • Can't really see this being very useful until they can correctly identify the owner's voice in a crowd of people standing outside in a wind. Until then I won't be buying anything with speech recognition. Why bother training a PDA if it doesn't recognize your voice in places you're most likely to need it? Having things read to you could definitely be useful in a PDA though.
  • STAR COLON FILE NOT FOUND

    ROOT AT LOCALHOST ARROW CURSOR

  • Why does there *have* to be. Speech as a method for controlling your computer has some severely limited function. Every time something interesting is posted, it *has* to be free and soon or well you might have to pay for it *gasps*

  • Maybe it's the psycological factor, but in reality using Linux for a PDA is...*looking for a word that won't start a flame war*...not-smart. Using Windows CE or Windows anything is not smart either. The idea that a smaller scale computer can handle a Macrokernel and do more work than a desktop is appaling. Go invent a microkernel base for PDAs. Make it short and to the point, then have it run the apps you need.

    Now on the topic of PDAs. I think the ultimate PDA would be a little thing that looks like the PalmPilot but w/o any buttons or screen inputs. On the screen is a talking head (AT&T In development) and it speaks to you (AT&T in devel, but really fantastic quality alread). It interprets what you say via speach recognition and *looking for the right word* a low level AI language interpreter. You would talk to it, like "Can you remind me to pick up some food?" or "John's e-mail address it blah at blah dot com and he is a moron." And then you can recall the info by saying "Who was john again?" Etc. Etc...like a portable secretary.
    Roy Miller
    :wq! DOH!
  • Talking head == easy to use interface

    The Head can display data on the screen too, what did you think it was going to do speak the whole thing out? You've gotta be kidding...
    Roy Miller
    :wq! DOH!
  • Make it a swedish blonde and to hell with Linux.
  • I don't know if any of you windows users out there have tried command based voice recognition ... in fact I think MS offers it for free ... I got it from a program here. StreamBox [streambox.com] which even gives you a lil wizzard that sits there and does text to speech as well. But the one thing still stands U N L E S S Y O U S P E A K C L E A R L Y ... with no background noise the program is virtually useless.

    Another thing... how much does it help to have a portable linux? Do you really care what operating system tells you that you have a doctors appointment in an hour?

  • I'd be happy to sell you all the vaporware you want ;)
  • HHmmm Open source project?

  • Ummm . . . you must mean voice recognition secruity.

    For those things, as far as the computer is concerned, no, you can't do a perfect impression of Sean Connery. Its not looking for sound patterns that can nessarly be heard by humans. It looks for small subtilities which are considered impossible to fake.

    However, this article is talking about a system that will allow you to give commands into a computer and it will act on them (a la Star Trek). In this case, yes, you might be able to pull off an impression of Sean Connery to the computer. But security isn't the point behind such a system, anyway.


    ----------

  • Which means that Bill will wait for them to make something cool and then make a half-baked port of it to Windows ;)


    ----------

  • I find it hard to believe that they can pull this off in a PDA. Most speech recognition tends to processor intensive. That is the number one reason most speech software is sitting on the shelf. Also the software requires training in many cases to make it easier on the software and the processor.
  • Hmm, I heard that same story but it I heard it worked with Philips Freespeech.

    While they were setting up the demonstration someone in the audience would have said "start" - "run" - "format c:" - "enter".

    The thing is, that this would not work enless Windows was installed on the D: drive (which is rather onlikely). "deltree /y c:\*.*" would have done trick though.
  • Yes, kind of funny in a nerdy sort of way. How many books were there, I only read the first 2.
  • By the way, not only did it not work well, I had to sit and "train" it for hours by reading it long passages of Treasure Island and Tom Sawyer.
  • Voice recognition does work if you Read The Fine Manual! I am a technical writer and use Dragon NaturallySpeaking Preferred USB 4.0 on a Windows 98 Pentium III with 128 MB. The only mistakes it makes are my own speaking mistakes.

    If it really worked, you wouldn't HAVE to read the Fine manual. Instructions = talk into microphone! Fact is: It works the more you use it (therefore it can adapt to your voice) but the early going is too rough for most.

    Right now, voice recognition just plain plain sucks. Learn how to use a DVORAK keyboard and you'll be far better off. And, you won't need a Coppermine with 512MB RAM!!!

  • I recently shelled out close to $200 for a speech recognition software (for PC)...now, it's somewhere in the corner of my room drawing dust. The thing simply didn't perform as advertised; most voice commands I had to repeat 2-3 times before the program picked it up. Perhaps I'm just being close-minded here, but I'm perfectly content with my current keyboard/mouse setup, and probably won't go shopping for anymore voice recognition software in the near future. Hay, typing is the only exercise I get nowadays...don't take that away from me too!

    ---------------
  • Actually, I was referring to voice recognition software as it applies to the general public, but point taken. Research should definitely continue on this front.

    ---------------
  • The great thing is it doesn't crash when it doesn't recognize a dictionary word *cough* (windows) *cough*

    "I'm sorry Dave an error 1 has occured while you were compiling"

    Damn...
  • Yeah, I also find it hard to believe that they could make decent voice-recognition software that would run on the very limited system resources of a PDA.

    Either:
    1) They made one hell of a breakthrough in voice-recognition technology that will have repercussions throughout the whole PDA and PC industry, with the elimination of the requirement that everyone who runs it has a Pentium III 800 or better system,

    *or*

    2) This is complete vaporware.
  • I would love them try to patent their version of linux. Anyone ever heard of the GPL?that renders any patent on it virtually useless. However, a hardware patent could probably come out good...
  • and it will speak you in the Voice of the Devil!!

  • Re:patents? (Score:2)

    by Anonymous Coward
    Why would they patent their version of Linux? The voice recognition is most likely not integrated into the OS...

    And I believe they deserve a software patent. People have been working on voice recognition for a long time, and it doesn't work all that great so far... if they did something neat, this is what patents were created to protect...

    How much fun would it be if this WAS integrated into the OS? You'd have to give it verbal OS calls instead of common-sense commands... lots of fun.

    E.
  • Does anybody remember a low-budget BBC sci-fi drama from the 1980's called <i>Star Cops</>? The programme's theme song was by Justin Hayward from the Moody Blues.

    Anyway, the main character (a detective called Nathan Spring who was sent out to police a small base on the moon) had this really neat PDA that he called "Box". It was a computer, internet terminal, telephone, diary etc. all rolled into one, and it had a voice interface. And a kind of personality too.

    I seem to remember in the end it self-destructed in order to take out some bad guy and save Nathan's life.

    Ever since then I've been waiting for these devices to appear. I can't be bothered with handheld computers as they are now, the interface is just too narrowband. I want my own Box.

    Consciousness is not what it thinks it is
    Thought exists only as an abstraction
  • Yah! An open-source voice-recogition SDK would be too cool for words. I don't think L&H would go for that, however. Their product line seems focused mainly on shrink-wrap Windows applications. No OSS vibes there :-(

    Alternately, there's IBM's ViaVoice [ibm.com] SDK, but it's closed-source, and I think it's still in beta. There's also CVoiceControl [kiecza.de], but it doesn't look like a very sophisticated implementation. (Then again, I haven't tried either of these). There's still a need for a free-as-speech, smooth-as-glass voice recognition library.

    ObOnTopic: Speech control is PERFECT for a PDA-type device. It gives you almost all the flexibility of a CLI, without the overhead of a keyboard. But methinks it'll be tricky to get it running smooth enough so I don't have to repeat commands, or otherwise utter them like two inches from the microphone :->
  • Erm... I work at L&H, and last tuesday, we bought Dragon... So we're not "generations ahead", Dragon simply doesn't exist anymore ;-)
  • Well, Microsoft owns 7 or 8 % of the stock in L&H. The fact that it runs on linux has to do with the fact that it was attempted on WinCE first, but didn't work, in fact. (I happen to work there, and the guy who led the project told me).

  • I don't know about those products, but for L&H Voice Xpress you need at least 64 Mb of RAM, and preferably even more. So I think those other software packages would need at least as much. Voice recognition isn't easy, ya know ;-)

    And it's not running on a Palm, it's running on a Strongarm II.

  • Even if the story is apocryphal, you *do* need to be careful to limit your voice commands to safe activities, because the stuff has never been 100% accurate, and at best Does What You Say, not Does What You Mean. "Oh, I Forgot C: was where the stuff lived" might also be heard as "Format C:"...
    So you pick a few dozen commands that you do often and that can't do major damage without at least some safewords around them.


    Voicetyping things into text input boxes isn't as dangerous - so you put some wrong stuff in a paper you're writing, and it's got the usual interjections from editing and real-world interruptions and phone calls. You can edit that later.


    Picking context-sensitive sets of things you actually want to talk to your computer about can be tougher...

  • DOS had trouble growing because it was designed for real-mode operation where you added capability by wedging more stuff into a small space - it wasn't made to multitask, and they wanted to retain backward compatibility with everything.


    Unix-like systems give you a lot of flexibility in letting things talk to each other, including keyboards and their substitutes, processes, etc.,
    and they're not picky about what hardware really exists as long as it's not too weird.
    The critical issues for porting voice to Unix are things like making sure the scheduler has enough hard real-time support that the voice recognizer doesn't starve, working within a multi-process environment, and dealing with kernel-userspace boundaries. For instance, if your voice recognizer provides context-sensitive vocabularies, how do you keep track of which context(s) belong to which processes, and if they're in the kernel or other protected storage space, how do you pass vocabularies to them efficiently?

    But most of that's pretty straightforward, and application level, and can't be worse than adding X Windows or NeWS was, and certainly not as difficult as adding TCP/IP had been.


    More importantly, if you want to build voice applications, what kind of services do you think an OS will need to support them? Are they available in Linux? Do you need to add them? Is there anything big you have to get rid of to make them work? Sure, you could junk it all and use a capability-based system like the
    [upenn.edu]
    Extremely Reliable Operating System
    or some microkernel thing. But what do you need?

  • A while back, a friend of mine worked at CompUSA (american computer superstore) as a greeter. Every day he would greet people as they came in and help them if they needed it. One day, a woman with sunglasses and a dog came in, and asked if he would help her around the store. John (my friend) was a little confused, as the woman was obviously blind.

    They talked for a minute and he asked a fwe questions, trying to figure out who the computer was for. He came to the conclusion that it was for her.

    He was helping her around the store when curiosity finally overwhelmed him, and he had to ask her why a blind person was in a computer store buying hardware. As it turned out, everything we do, she did. She was a computer geek. She was even a programmer. I'm not sure whether or not she installed her own hardware:)

    She used voice commands for everything. Including writing code.

    This point of this diatribe is to point out that while the keyboard and mouse may be fine for you, there are those who need the software to be productive.

    As for the exercise, theres always masturbation.

  • Your own PDA is trained with your 'voice'. Have an external plug on any system, then plug your pda into it. Now you have a voice interface anywhere you go.
  • I don't like the word 'patent' in the first sentence of the paragraph about this thing. Is it a software patent? I am a bit sceptic about this thing......

    Grtz, Jeroen
  • I have used Dragon Naturally Speaking as well as IBM's ViaVoice and neither seem to work too well. I don't think I studder or anything and as far as I can tell I speak pretty clearly. Neither worked well for dictating and they slowed down my computer noticeably. (P200, 48MB) How well can this possibly work on a Palm? Does anyone know what Speech-to-Text engine this uses?

  • Re:Shades of 2001 (Score:3)

    by technos ( 73414 ) on Friday March 31, 2000 @11:16AM (#1158240) Homepage Journal
    I can see that. When it comes out next year, L&H will change their name to H And L, so that they can call it the 2001 H.A.L. Or, if they chose a more subtle prank, they'll call it the L and H model 1002.

    'Holy mirror images, Batman!' -Dick Grayson.
  • One nice thing about voice-PDAs as opposed to laptops or palmtops is that they don't need to be accesible or even really small. The part that has to be conveniently accessible is your headset, and the rest can be in a pocket or belt pack or backpack, or on a PC on your desk, or off at the other end of a network somewhere. Some voice-dialing cellphones, for instance, keeps the voice recognition intelligence back at the central office or cell site, rather than wedging that much power into your handset.

    One negative about Voice PDAs, like cellphones, is that you spend time in public talking to yourself while you walk down the street. (Here in my part of San Francisco, half the pedestrians do that because of cellphones, and half because of substance abuse...)

    If you add visual displays, e.g. i-Glasses, you're adding extra volume and weight, and you get to walk down the street in Gargoyle mode :-)

  • Reminds me of a story I read... (Score:3)

    by Ater ( 87170 ) on Friday March 31, 2000 @11:14AM (#1158242)
    I dont know if this is a true story, a joke, or just a cute little urban legend, but it also regards voice recognition software. This company had just developed a new, really powerful voice recognition program (this was in the old days when DOS when the most commonly used OS), and they were showing off the software at a press conference. The developers encouraged the reporters to yell out commands and watch the software in action. And immedietally, from the back, some wise guy shouted out "FORMAT C:\, RETURN!" The software worked...

    Wonder if there could be an analogous action for this new Palm software.

  • Shades of 2001 (Score:3)

    by meckardt ( 113120 ) on Friday March 31, 2000 @11:00AM (#1158243) Homepage

    And when they come out with a marketable version, it will be called HAL.


    Gonzo

  • Some more info... (Score:4)

    by Dilbert_ ( 17488 ) on Friday March 31, 2000 @02:05PM (#1158244) Homepage
    First off, I work for L&H, so if I sound biassed, hey, they pay for my bandwith... But at least I am an engineer and not a salesperson ;-)

    I saw a demo of this thing a couple of weeks ago. Basically what they did was port the Voice Xpress engine to linux, and make it work on a Strongarm II processor. Right now all that was built was a single prototype, and some issues like battery usage are still to be worked out before the thing goes into production. (Estimate : end of this year)

    What was also done, was building in the L&H Realspeak synthesized voice. This allows real dialogues to be held with this device. For instance :
    -Check mail !
    -You have five new messages
    -Summarize !
    -Message one, sender is J. Random Hacker, Subject : kernel hack. Message two, sender is Bill Gates, Subject is Make money Fast...
    -Read the first message !
    -Hi there... I just finished a patch for the latest kernel update... blablabla...
    -Reply !

    You could then use this to dictate an e-mail (because it uses a full Voice Xpress engine), or order books on Amazon (If you wanted to shop there) using WAP. All in all, a pretty nifty device. I want one myself ;-)

    And no, it was not vapourware, it really works : with the VX engine you can already get 95% accuracy if you want to, with a large vocabulary. The smaller the vocabulary, the better the recognition. How many commands do you need to read your e-mail ? You do the math.

    Oh, yeah, it also has a stylus and screen that fold away into it, just in case you really wanted to read or write stuff.

  • Adding voice recognition is the wrong idea (Score:4)

    by leshert ( 40509 ) on Friday March 31, 2000 @12:19PM (#1158245) Homepage
    In general, taking an operating system and strapping a new paradigm to it is a Bad Idea.

    When Microsoft took DOS, a single-user operating system, and added Windows to it, they ended up with a really terrible hack that didn't run either, up until about version 3.1.

    When Microsoft later took Windows and added pen support (not CE, but Pen Windows--read your history!), it flopped. Windows wasn't suitable.

    When they attempted to port a subset of NT to pen-based devices, they got CE, which has underperformed.

    On the other hand...

    When Apple abandoned the Apple II and designed the Mac as a graphically-operated machine from the ground up, they got a great platform.

    When Palm threw out common notions of a shrunken PC and designed their device from scratch, they won.

    My point is that a good voice-controlled system needs to be designed as a good voice-controlled system. Strapping it on after the fact won't cut it.

  • Linux PDA speech CLI (Score:5)

    by joshv ( 13017 ) on Friday March 31, 2000 @11:07AM (#1158246)
    Me: "p-w-d"

    Computer: "slash"

    Me: "l-s"

    Computer: "slash u-s-r, slash h-o-m-e, slash b-i-n, slash b-o-o-t, slash e-t-c..."

    Me: "cd slash e-t-c"

    Computer: *silent*

    Me: "vi profile"

    computer: (reads file contents)

    Me: "quit"

    computer: "error"

    Me: "exit"

    computer: "error"

    Me: "wq"

    computer: "file is read only"

    Me: "q!"

    That's my kinda computing

    -josh

Slashdot Top Deals

Whatever is not nailed down is mine. Whatever I can pry up is not nailed down. -- Collis P. Huntingdon, railroad tycoon

Close