Innovation: Speech prediction software

If people who finish your sentences drive you crazy, it's a safe bet that you're probably not going to be nuts about new software that can do just that.
It's been dreamed up as a speech-recognition equivalent to the predictive texton cellphones. Mutter a half-considered thought into the microphone and the software will plunder a database to complete half-formed words or sentences - in Japanese, at least.
The system looks for fragments of words and other signs of hesitation such as filler sounds that Japanese speakers use when searching for their next phrase, just as English speakers "um" and "er".
It can work backwards too. If you're using the voice-controlled jukebox made to demo the idea and ask for a song by "someone, er, Jackson" it will offer up Michael, Janet, and even Joe.
You can imagine how that could be useful for requesting songs from a car's stereo while driving, or requesting a new location from a GPS device. [click heading for more]