Active Topics

 


Reply
Thread Tools
Posts: 46 | Thanked: 31 times | Joined on Jun 2010 @ Lebanon
#11
Originally Posted by joerg_rw View Post
voice-call via dbus: should be rather simple, as long as you start the speech input engine on headset pushbutton and use a small set of pretrained contact name vocabulary.
/j
I think the engine takes quite some time to load, it would have to be preloaded some time before that or loaded on first press, then just called (sort of a mute/unmute). The easiest solution I think for the contact names: a dynamically built (the user would choose the names he wants to voice call) jsgf grammar since that would decrease the errors dramatically and hopefully remove the training processes which is abit complex in sphinx as far as i tried.

I know a bit about this as I was working on an AI/Voice Assistant (both on PC using Java, and on Maemo). No solid code yet, and I can't find the time to work on it. However, I'll try to help out as much as I can.

Cheers for the initiative OP
 

The Following 2 Users Say Thank You to karimko For This Useful Post:
joerg_rw's Avatar
Posts: 2,222 | Thanked: 12,651 times | Joined on Mar 2010 @ SOL 3
#12
please also refer to http://talk.maemo.org/showthread.php...10#post1038610 Gesture Recognition Daemon, which would integrate nicely with this one, and serve as both trigger and generic framework for system wide voice control of arbitrary apps (as long as there's any API to control the app - even if it's only the kill -9 cmd ;-P)
__________________
Maemo Community Council member [2012-10, 2013-05, 2013-11, 2014-06 terms]
Hildon Foundation Council inaugural member.
MCe.V. foundation member

EX Hildon Foundation approved
Maemo Administration Coordinator (stepped down due to bullying 2014-04-05)
aka "techstaff" - the guys who keep your infra running - Devotion to Duty http://xkcd.com/705/

IRC(freenode): DocScrutinizer*
First USB hostmode fanatic, father of H-E-N
 

The Following 2 Users Say Thank You to joerg_rw For This Useful Post:
Posts: 291 | Thanked: 435 times | Joined on Apr 2011 @ RO
#13
Originally Posted by mc_teo View Post

After this I raw the Script here from the CMUSphinx example, tweaked to work for pulseaudio, http://pastebin.com/zCYzX65Z
Anyone, a little help

I got this error
SYSTEM_ERROR: "dict.c", line 262: fopen((null),r) failed ; Bad address

I must specify the dictionary file, as I understand ...but where...not clear what file should I change
 
Alfred's Avatar
Posts: 855 | Thanked: 612 times | Joined on Oct 2010 @ Germany
#14
Guys, i wonder if somebody is still working on it?
Then we could beat the **** out of Siri
__________________
Reps are just one click away: Extras | Extras-Testing | Extras-Devel | My-Maemo | CSSU |
Transform your lock screen into a weather forecast Thanks button ================>
 

The Following 5 Users Say Thank You to Alfred For This Useful Post:
Boemien's Avatar
Posts: 770 | Thanked: 558 times | Joined on Mar 2010 @ Abidjan
#15
Hahahaha! I knew somebody would say such a thing! Let's face the power of innovation of Apple, or at least the fact that they do better than other brands!!! I wonder what surprise will be in the iPhone5!!!
__________________
If you find this post useful for you, or for another member, just hit the Thanks! button
 

The Following 2 Users Say Thank You to Boemien For This Useful Post:
Alfred's Avatar
Posts: 855 | Thanked: 612 times | Joined on Oct 2010 @ Germany
#16
Well, i tried and it actually kept up pretty good if you are not too close to the mic, especially taking into acount, that I am Russian.. I guess if smbd keeps developing it, we can actually try to use it on the daily basis.
__________________
Reps are just one click away: Extras | Extras-Testing | Extras-Devel | My-Maemo | CSSU |
Transform your lock screen into a weather forecast Thanks button ================>
 

The Following 3 Users Say Thank You to Alfred For This Useful Post:
Posts: 5,795 | Thanked: 3,151 times | Joined on Feb 2007 @ Agoura Hills Calif
#17
I hadn't noticed that this was sort of working till today. It's not exactly Dragon NaturallySpeaking.

Can someone give an intro explaining what can be done? I can run the Continuous version from the command line and it recognizes some words that I say.

In Dragon NaturallySpeaking, you say "What Can I say" and it gives you a guide to what commands you can use.

What can I say with Pocket Sphinx? Or should I google for a basic guide?

I know I'm asking a bit much, but does it train to learn your speech? In other words, will recognition get better through practice?
__________________
All I want is 40 acres, a mule, and Xterm.
 

The Following 3 Users Say Thank You to geneven For This Useful Post:
Posts: 291 | Thanked: 435 times | Joined on Apr 2011 @ RO
#18
Originally Posted by Alfred View Post
Well, i tried and it actually kept up pretty good if you are not too close to the mic, especially taking into acount, that I am Russian.. I guess if smbd keeps developing it, we can actually try to use it on the daily basis.
Hey Alfred...please help me..and tell me what you installed and how, because on my phone not working
I got this error
SYSTEM_ERROR: "dict.c", line 262: fopen((null),r) failed ; Bad address
 
Alfred's Avatar
Posts: 855 | Thanked: 612 times | Joined on Oct 2010 @ Germany
#19
Okay, i uninstalled everything, because it's not optified, will try again tomorrow and report back.
__________________
Reps are just one click away: Extras | Extras-Testing | Extras-Devel | My-Maemo | CSSU |
Transform your lock screen into a weather forecast Thanks button ================>
 

The Following 2 Users Say Thank You to Alfred For This Useful Post:
Posts: 291 | Thanked: 435 times | Joined on Apr 2011 @ RO
#20
Originally Posted by Alfred View Post
Okay, i uninstalled everything, because it's not optified, will try again tomorrow and report back.
eeee...I will die until tomorrow
but why I have problems and you not?
 
Reply


 
Forum Jump


All times are GMT. The time now is 09:45.