The KLearnNotes2 Handbook | ||
---|---|---|
<<< Previous | Voice input - talk to your computer! :) | Next >>> |
There are two ways of voice recognition:
- computer learns, how people pronounce things in a particular language, and then recognizes a phrase by comparing it to its "dictionary" of phrases;
- computer records few samples of a phrase spoken by a particular speaker, and then recognizes it when it is spoken again.
you need to have the "dictionary" recorded or prepared by others - this requires adding in each distribution very long files extra
the dictionary is obviously dependent on the language - as far as I know there are free dictionaries only for English: you would have to speak to your computer in English (I mean: very properly pronounced English!) or it would not "understand" you
recognition works fine if a context is available, e.g. for belleslettres texts or long phrases; it works awfully bad for single-sound phrases (like notes' names).
The price to pay is that starting with this would require that each user makes some setup. I expect it to take (including reading the quick start instructions) less then 5 minutes for a novice, unexperienced user to make first voice-answered test. :)
<<< Previous | Home | Next >>> |
Voice input - talk to your computer! :) | Up | Voice input - Setup details, hints and tricks |