Slashdot Mirror

← Back to Stories (view on slashdot.org)

Thai Students Score a Prize For Speech Software

Posted by ryuzaki0 on from the illiterate?-write-for-free-help dept.

Julie188 writes "A team of four Thai students beat out 10,000 competitors to win the $25,000 prize in the Microsoft 2007 Imagine Cup. Their project is text-to-speech software in which computers read aloud typed and handwritten commands. The software will allow people who can't read to interact with a PC. Imagine Cup judge Rand Morimoto has been blogging on the whole experience — from his video of the opening ceremonies to how contestants swilled free Cokes to keep themselves awake during the 24-hour, no-sleep phase of the competition."

3 of 77 comments (clear)

  1. Blind people want to use Vista by Dancindan84 · · Score: 5, Funny

    Cancel or Allow?

    --
    "Always forgive your enemies; nothing annoys them so much." - Oscar Wilde
  2. Re:Microsoft by andrewd18 · · Score: 5, Informative

    I'm aware that this is Slashdot and we can't have anything positive said about Microsoft, but you could at least show the full story, not just the biased, edited clip.

    Here's the full clip: http://www.youtube.com/watch?v=kX8oYoYy2Gc

    Yes, it's not perfect. But no, it's not as bad as that clip makes it.

  3. Re:More useful links... by mscoder610 · · Score: 5, Informative
    I just came back from the Imagine Cup software design competition, and I saw the presentations for the top 6 software design finalists. More details about the Software Design part of the Imagine Cup:
    • The "24 hours straight through" part of the story doesn't apply to Software Design. It applies to some other of the challenges like Algorithms, Photography, and Short Film.
    • Software Design teams came up with the idea themselves (to improve education), and had multiple months to work on it.
    • Thailand's winning solution isn't just a text-to-speech thing, as the story implies. What it basically does is: Someone with their program and a webcam can place any book in front of the webcam. Their solution not only applies the text-to-speech stuff (for people who can't read the words), but it also tries to make the book more "visual". On a single page, it basically looks through each sentence for the main ideas of it, i.e. actions and verbs. Then it tries to show those ideas visually, with a picture or video. It was a pretty neat project.
    Hopefully that clears things up a little. I looked around for a page with a full description of their project, but I wasn't able to find one.