Slashdot is powered by your submissions, so send in your scoop

 



Forgot your password?
typodupeerror
×
Technology

Voice Recognition For The Visually Handicapped? 32

MrIcee asks: "I was recently contacted by an individual who is extremely visually impaired. He wishes to be able to user voice recognition in his PC to dictate letters and to control his web browser and other software. In examining the available software (such as Naturally Speaking, etc) all of them require a fairly involved training session. The problem with training is that they tend to display paragraphs for him to read - but he is unable to see the words clearly enough and fast enough for proper training (even though he can use JAWS for reading screen text). I have seen references to Kurzweil VOICE software, but it seems dated and there is no good indication that it will work as promised. Does anyone out there have experience in voice recognition software that requires minimal or no training?"
This discussion has been archived. No new comments can be posted.

Voice Recognition For The Visually Handicapped?

Comments Filter:
  • Dragon.. (Score:4, Informative)

    by zulux ( 112259 ) on Tuesday January 21, 2003 @04:08PM (#5128924) Homepage Journal
    The version of Dragon that I'm familiar with uses plain old text files for the imput for it's training session. I'd imagine you could replace them with somthing that it also avaiable in brail.

  • And just go over their house for an afternoon and help them get it trained. If they are too far from you, have them find someone closer. Reading paragraphs isn't rocket science - people are by and large happy to help out. All they need do is ask.
    • The issue is that the software is trained for the specific voice. Even if someone is there to help, the phrases have to be spoken naturally by the person who will use the software. This process can take many hours to reach any kind of accurate training. It seems that it could be possible to memorize all of the training phrases and use the help of a friend for seeing the start and stop cues but it's going to be a long tedious process.
      • Another idea, if he's goign to stick with Naturally Speaking, is to use a text-to-braille converter (assuming he can read braille) for the training sessions.

        Here [epix.net] is a link to a page that discusses some of those braille output technologies.

        Hope this helps
        --Turkey
  • I'm sorry, but the current state of the art in available voice recognition (Dragon, of course) is pretty unreliable on its own. With several hours of training, it gets about one in twenty words wrong. It also doesn't understand new words and many proper names, like Kazakhstan, Khomami, Schwarzkopf, etc. As long as he only speaks to people named Greg and doesn't talk about the 60 Palestinian shops burned near Tulkarm, he should be OK. Otherwise, he will have to recognize that the imputing software made a mistake (which, as you said, is unlikely), highlight the text, and replace it manually with a keyboard. And without training, that accuracy drops precipitously.

    Why do all of that? He's vision impaired, he should have a friend teach him to touch-type.

    Browser / Program control is easy. Get a Mac. They have had built-in voice-based program control with speakable items for about ten years now, and there are products that extend the existing control base.

    The google directory [google.com] has links to a lot of speech recognition companies, but I still think your client would be most happy with OSX's recognition options [apple.com]. It doesn't have to be trained for a voice, though its full power does require some Apple Scripting. And there are many products [apple.com] that build on apple's relatively solid base, if you choose not to script "go back" to "apple-B" in the browser yourself. Having used it myself in the past I can confidently say it exists, and used to work at least most of the time.

    That's more than can be said for most voice-recognition products. Bring him to an Apple store, and have him try it out. If you go to CompUSA or another superstore, bring your own apple guru to show you.

    • Thanks for your advice. I agree with you on all you say. The gentleman I am discussing is in his 70's and is unlikely to want to switch to a Mac (not that I'm biased, I'm on a Mac at the moment myself and would not hesitate to mention it to him). While he does know how to touch type, the problem is that even super big words are very hard for him to see *quickly* (that is, with text bigger than I can stand, he still takes about 5 to 10 seconds to make out each word)... thus the training session would be hugely complex for him.

      Another friend suggested him getting a 50 inch plasma screen so the text is REALLY BIG... also probably not a bad idea.

      PS, being palestinian myself, I also enjoyed your analogy.

      Aloha

  • Some voice recognition software came with my SBLive Platinum 5.1.

    It worked without training. It worked for all menus for all programs, even ones not designed to be voice-recognizable. It worked in one try.

    This is a problem?

  • I would check with a Hearing Impaired Center that would have some kind of other alternative to voice recognition software. All of the ones I've seen or heard about necessitate training of some kind. Or inquire at the individual companies that offer these programs to see what they have to say.

    But, I might suggest somehow having the training sessions read onto tape so that all that need be done is to repeat aloud the recorded audio that dictates the training passages. That of course would still require some help or slow process to make useful, but they wouldn't have to read anything.

    I also know that most of these programs come with a 'read aloud' function that enables you to hear everything you type. You could copy the training passages into them and have them read back to you while you are conducting a training session. That could make it easier.
  • Apple has a great speech recognition and speech rendering engine [apple.com] built into OS X along with a full complement [apple.com] of features for disabled people. My father with severe macular degeneration can use my iBook reasonably well with these features and some applescripts [apple.com] built using these commands [apple.com]. I've added little scripts to Safari and Mail.app to help him out, but the Speakable Items features on their own are quite complete.

    I just whipped up a script to read a selected bit of this article in Safari, save it to an AIFF file then use iTunes to convert that AIFF file to an mp3. Listen to the result here [geocities.com].

  • My suggestion is to have someone sit by him and quietly feed him the training text a sentence at a time. Speed was not an issue last time I trained Dragon, just saying the words clearly was important.

    Once he is done with that he can use the vocabulary builder (I think that is its name). This feature allows him to load documents he has typed in the past and read it back to Dragon. He could then have a brail printout of it to follow and speak.

    The natural language processing problem is going to be a tricky one for some time. I know that I want a nice golden protocal droid ;-D
  • Macos has voice recognition built in, you can control your browser and it will dictate for you. also, ibm's viavoice is available for speech recognition.
  • I did a presentation on IBM's ViaVoice software for a Linux event a couple of years ago. I'm not sure what the current availability is of this offering, but at the time it was rather good.

    IIRC, the training was very short, but it would require help from a sighted person (reading text and adjusting microphone sensitivity). It's all Java and it runs on Linux. If he just wants to enter text, it's okay. It comes with its own editor that can do simple markup and save to RTF format. It required a fairly beefy computer for the times (I think 256MB of RAM and a 500MHz processor) but that type of hardware is more affordable now. I remember it being smart enough to use context in its recognition (e.g. "the nose knows").

    PS: I was struck by one of the earlier comments that stated that your friend should learn to touch-type. I'd be suprised if your friend doesn't already know how to touch type. It would seem to be the more efficient and accurate way of communicating with a computer. Forget mice... I hate mice! I myself use the keyboard whenever I can and I'm sighted. However, if you were using your hands to *read* and you wanted to dictate while scanning some braille, the need for voice recognition becomes manifest.

Love may laugh at locksmiths, but he has a profound respect for money bags. -- Sidney Paternoster, "The Folly of the Wise"

Working...