in reply to Re: Re: Image Character Recognition
in thread Image Character Recognition

I guess the issue with implementation is that the graphic image is easy to randomly generate using software, but the sound byte is much more challenging to generate!

Not really. Just create a series of files each with it's own audio for a single letter, then string them all together and send the concatenated audio. We have an application that uses a similar technique to generate real-time navigation information for ships.

  • Comment on Re: Re: Re: Image Character Recognition

Replies are listed 'Best First'.
Re: Re: Re: Re: Image Character Recognition
by cees (Curate) on Dec 05, 2003 at 00:52 UTC
    Just create a series of files each with it's own audio for a single letter, then string them all together and send the concatenated audio.

    But wouldn't it then be easy to generate a program that knows about the signature of each of those letters? The challenge is randomizing the sound of each letter so that it is easy to understand for a human, but hard to recognize by a program.

    This is especially tricky since there is already some really good speech recognition software out there.

    Perhaps you can overlay the sound of the letters/words with some music, or something else that will not affect the ability of the person to hear the word.