Hi,

can anyone tell me if N900, or better to say Maemo5 has a built in speech recognition system? Available by some API?

I know I can port some linux projects, but that's a paint.
I hope it has something built in.
If not can someone tell me which projects are among the best in this field, and is there any easy way to port them to Maemo?

Note: I'm looking for a speech-to-text STT, not the other way around (TTS)

Thanx in advace

Nothing build in. Sorry.

That's a shame...
The more I look into this system the more disappointed I get.

Even 3310 had a speech recognition algorithm for speed dialing. I really can't see, why after 10 (or more) years and a few huge technological steps, they don't include these basic features in their top of the line phones.

So, anyway do you have any suggestions for porting linux libraries to Memo? Which ones are the best by performance? And are there any already ported?

did some research on ocr and tts-engines. while google provides us with a perfect open-source-ocr (did set it up in easx-debian) i couldn't find a state-of-the-art speech-recognition-system.

the following open-source-project was my starting-point:
http://www.simon-listens.org/index.php?id=122&L=1

it uses a japanese continuous-stt-engine, which seems to be equal/better than most commercial ones.

however it is difficult to get all the necessary sounds/statistical data. though there are open-source-projects which are collecting these.

please keep us up-to-date if you have something working on desktop or N900. i use windows vista's speech-recognition within a virtual machine in ubuntu (just out of interest for stt).

i never really used any stt-system on my desktop/mobile for productive purposes. even on my phone long-pressing a key was far superiour. but thats just my personal experience..

tts (text-to-speech) is not such a big problem
there are some web services that can do it pretty good
like: Google translate (has English pronunciation now), Ispeech, loquendo engine ...

speech-to-text is my problem
i can't exactly tell why aren't there any online services that can do this, except because of potential slow upload of audio files to server
obviously i have to implement it on the client, which is in this case N900 and Maemo

sorry i meant stt (quite confused as i am typing this while bringinhg my kids to bed) have a look at simon listens. there are some impressive youtube-videos for this speech-recognition-system.

See Carnegie Mellon's PocketSphinx. (Some assembly required...)

Check gnome-voice-control of GNOME, I've ported to maemo 4, and it work NOT so good just like gnome-voice-control, further more it's CPU consuming, from my point, it can only be regarded as a prototype SW.