i never used voice dialing on any of my phones and the N900, well, it replaced my Netbook. Do i want voice dialing on my netbook? No. So i neither expect nokia to develop it nor would i be interested in a community developed voice dialing.
Yes, you can do voice dialling (2 Ls? wrong spelling!) now on maemo, it is working.
1) Install nitdroid froyo
2) install voice patch
3) tada, you have voice dialling ( really, 2 Ls? ), today. Sorry, if it is not out-of-the-box
bun
Could you explain these three steps in some more detail? I would really like to have voice dailing on my N900. Just bought a BH-905 headset... Thanx in advance.
Quick reply...
Not voice dialing, but continuous speech-to-text recognition for all programs (turn it on/off in settings), which would be completely configurable, and would include voice dialing, voice browsing (ask weather forecast aloud, and hear and see the answer), voice photographing (useful to capture a photograph of something moving; imagine trying to photograph a shy animal which is afraid of you, but not afraid of the camera), voice routing to a place/rerouting when you change your mind, etc.
This would be useful. Don't restrict yourself. Implement it as some kind of background daemon.
Not voice dialing, but continuous speech-to-text recognition for all programs (turn it on/off in settings)
It's one thing to match pre-recorded samples to microphone input, and an entirely different matter to do complete speech-to-text recognition. Try for example Google's own recognition system: even with all the processing power their servers possess the recognition system can't achieve more than about 70% accuracy and that is when the speaker speaks very, very clear. If the speaker doesn't speak all that clearly, if there is any kind of background noise, if the person speaks some dialect, or if (s)he has some sort of an accent to the speech the correctness of recognition drops sharply.
Then there's the issue of N900 being a small device with limited microphone capabilities: there is not enough processing power to do accurate recognition, and the microphone would receive sufficiently clear input only when spoken very near to it.
Indeed, as I just said, it's easy enough to match speech to pre-recorded samples, but doing whole, full, non-pre-recorded sentences? No, not even today while it's been under development for decades now.
