I write code to analyse voice recognition results. It works well, but is quite a lot of stuff to do to make it workable. See my free (free at present anyway) App called Spelling in the market.
On Sep 2, 5:16 pm, moa <[email protected]> wrote: > Hi, > > Is it possible to use the voice recognition api in order to handle a > known set of commands yet? > > For example; > > Text to speech prompts "Say Yes or No" > > User says "no" > > VR matches this against a specific valid vocabulary containing only > "yes & no", and then returns "no". > > Can you do this yet? > > Last time I looked you could not. The VR would match against a full > vocabulary and user saying "no" would come back with things like > "snow" and so on. > > The other BIG problem was that if the VR got no match a "Retry" dialog > was displayed, this needed to be dismissed by using the screen, which > meant the the voice control process failed at this point, terminally. > > Is there any closer to being usable in 2.2 ? > > Thanks in advance for any feedback. -- You received this message because you are subscribed to the Google Groups "Android Developers" group. To post to this group, send email to [email protected] To unsubscribe from this group, send email to [email protected] For more options, visit this group at http://groups.google.com/group/android-developers?hl=en
