Sponsored links

Go Back   MP3Car.com > Mp3Car Technical > Software & Software Development > Front Ends > Road Runner


Reply
 
Share Thread Tools Display Modes
Old 05-18-2005, 11:51 AM   #1
Constant Bitrate
 
ruairi's Avatar
 
Join Date: Jan 2005
Location: Spain
Posts: 165
ruairi is on a distinguished road
SpeakEasy Voice Recognition - Beta 1

I've created a Voice Recognition app, my aim is to create a simple Voice Recognition Interface that is easy change and reduces false recognised commands. And to allow you to configure the setup the way you want it.

So I've taken the features I like from NaviVoice & Bruno and built my own Voice recognition app: SpeakEasy VR.

SpeakEasy VR unique features:
1. Highly customisable configuration
2. Predictive help to complete command
3. Interactively set a acceptance threshold for valid recognised commands
4. Simple interface to change voice commands (car friendly resolution)
5. Locking of command groups also enable/disable comand groups by voice
6. Can control and application that has a SendMessage, HotKey or TCPIP interface. I'll make a Girder importer eventually if it is popular.
7. Logging of voice commands to figure out which commands work well or badly in you car (with a noisey car engine a Voice Recogniser can pick up false commands). So this is a good way to figure out if you need to alter some voice phrases.



Ignore my orange/black RR skin that's my own funky colored RR skin. The window to look at is the slightly transparent white bix on the top left and in the center. The top left box is clickable to start the engine. The center box displays while you are talking. You can voice activate the center box as well and set the transparency levels to your liking.

I have a worked Beta if anyone is brave enough to try it!
----------------------------------

BTW, Interpreted text in GREEN means that it was recognised the accuracy was ABOVE the threshold which you set in the slider. If the text is RED the it was recognised but BELOW the threshold.

The Threshold is between 0% and 50%. Setting it to 0% means that anything that is recognised is executed. Set the value higher mean that you have to speak more clearly and precisely. I have a Irish accent and it seems to not work so well with it so I set the threshold high to about 25%, it also reduces false recognised phrases produced by car noise and MP3 playback. As you speak you'll see the accuracy of each phrase that is recognised, try to figure out what accuracy works best for you and set the slider threshold level to just below what you normally get for the accuracy. I find that for some phrases I need to turn it way down so that it is recognised, while other phrases get close to 100% no problem.

I'll write up some documentation in the next release if there aren't too many bugs/crashes

Last edited by ruairi; 05-18-2005 at 02:54 PM.
ruairi is offline   Reply With Quote
Advertisement
 
Advertisement
Sponsored links

Old 05-18-2005, 12:02 PM   #2
Maximum Bitrate
 
fantomas's Avatar
 
Join Date: Nov 2003
Location: CT
Posts: 754
fantomas is on a distinguished road
looks good. im glad to see more people developing voice recognition software. i might get around to trying it in a week or so but right now life is just a tad too hectic for me
__________________
rebuilding carpc... kinda..
fantomas is offline   Reply With Quote
Old 05-18-2005, 12:05 PM   #3
FLAC
 
-zip-'s Avatar
 
Join Date: Sep 2004
Location: Ontario/Canada
Posts: 1,141
-zip- is on a distinguished road
I will give it a go! Using Frodo in the car does it matter? I have RR but use Frodo.
__________________
Carputer
Installed Since April 2, 2005
Intel D201GLY|Fusion Brain|Audigy2 NX||ODBPros ODBII|Engenius362ext |Motorized lilli|GPS Rikaline 6010|Opus 150|Powermate|Ergonomic Touchpad|
Sound Stage
Eclipse CD8455|MTX TA3404+421D|Infinity Comps|ID 12" Sub
-zip- is offline   Reply With Quote
Old 05-18-2005, 12:10 PM   #4
Constant Bitrate
 
ruairi's Avatar
 
Join Date: Jan 2005
Location: Spain
Posts: 165
ruairi is on a distinguished road
Here's a screenshot of the vocabulary editor. Not as pretty because of the screen size on Lillput but it's functional and easy to use.



Left box contains all the voice commands center panels allow you to edit the selected command. Right panel allows you to choose which commands you want from all the available commands from that app.

The green text list in the center with RR:: blablabla shows the commands that would be triggered if you say the voice phrase. It's close to what NaviVoice does with Macros but I have yet to do mouse clicks. I know NaviVoice has macros but I'm not sure of it's functionality.
ruairi is offline   Reply With Quote
Old 05-18-2005, 12:11 PM   #5
Constant Bitrate
 
ruairi's Avatar
 
Join Date: Jan 2005
Location: Spain
Posts: 165
ruairi is on a distinguished road
@-zip-

I am working my way through the Frodo Girder file to figure out all the sendMessage/COM commands, once I've got all the commands I'll add them to the XML settings file and it's just a matter of editing the vocab to your needs.
ruairi is offline   Reply With Quote
Old 05-18-2005, 12:21 PM   #6
Newbie
 
Join Date: Oct 2004
Location: Madrid, Spain
Posts: 27
Balki is on a distinguished road
Hi ruairi.

I would like to try your voice recognition software. It looks really good!!
Where can I download it?

PD: I am also spanish, from Madrid.
Balki is offline   Reply With Quote
Old 05-18-2005, 02:22 PM   #7
Raw Wave
 
Laidback's Avatar
 
Join Date: Oct 2003
Location: Madrid
Posts: 1,983
Laidback is on a distinguished road
I'll try it, give us a link!
__________________
Laidback

Laidback Carputer
Laidback is offline   Reply With Quote
Old 05-18-2005, 02:47 PM   #8
Constant Bitrate
 
ruairi's Avatar
 
Join Date: Jan 2005
Location: Spain
Posts: 165
ruairi is on a distinguished road
Here it is, let me know if it crashes. I expect it to!
ruairi is offline   Reply With Quote
Sponsored links
Advertisement
 
Advertisement
Old 05-18-2005, 03:55 PM   #9
Raw Wave
 
Laidback's Avatar
 
Join Date: Oct 2003
Location: Madrid
Posts: 1,983
Laidback is on a distinguished road
Quote: Originally Posted by ruairi
Here it is, let me know if it crashes. I expect it to!



WinXP Pro SP2
.net 1.1

I get this on starting...
Attached Images
 
__________________
Laidback

Laidback Carputer
Laidback is offline   Reply With Quote
Old 05-18-2005, 05:54 PM   #10
Constant Bitrate
 
ruairi's Avatar
 
Join Date: Jan 2005
Location: Spain
Posts: 165
ruairi is on a distinguished road
@Laidback Cheers, I have a absoluted directory address in the settings file for the Vocabulary folder, So it would only work on my Dev machine. I've fixed this now, i hope! Please re-download and try again.

Also I've added complete FreeDrive command support, click on setup... to add in new commands.

A bit of help if you say "Show help" it will list all vocabulary commands that you can say. It is a little transparent, but the \Vocab\ folder can have as many ini files as you want and they will all be loaded when yuou start the app or press "Reset" button.
ruairi is offline   Reply With Quote
Old 05-18-2005, 08:20 PM   #11
FreeDrive Creator
 
CdRsKuLL's Avatar
 
Join Date: Feb 2004
Location: Manchester
Posts: 3,196
CdRsKuLL will become famous soon enough
looks good this m8.. I will add some more sdk commands this week for you now that speedcams are included.. would be nice to add these through voice

:-)

CdR
CdRsKuLL is offline   Reply With Quote
Old 05-18-2005, 09:00 PM   #12
FreeDrive Creator
 
CdRsKuLL's Avatar
 
Join Date: Feb 2004
Location: Manchester
Posts: 3,196
CdRsKuLL will become famous soon enough
ok had a quick play.. seems to work fine for about 3 or 4 mins, then the main screen disappears and nothing happens, the only way to close it then is by taskbar manager. Also.. 1st request :-) would it be possible to make it work like a multi remote control.. so say you are using freedrive.. you say freedrive once.. then any commands you wish, rather than having to say freedrive all the time.. like you would press dvd on the remote then all the keys are sent to the dvd.. then if you want to use roadrunner you say roadrunner, then all commands are sent to that app. ?

Also it took me a while to figure out I needed to load the ini file.. could you load this as a default one on startup maybe ?

this looks like its got loads of potential good work m8 :-)

CdR
CdRsKuLL is offline   Reply With Quote
Old 05-19-2005, 01:34 AM   #13
Variable Bitrate
 
Join Date: Jan 2004
Posts: 232
FunkDaMonkMan is on a distinguished road
Just tried it out!

I really, really like the UI on the main screen. The help list seems to work really good.

I think that the settings builder could be a bit easier to use.. but this is your first version.

Overall, very nice...

I will have some sort of voice command help in the future.. but it is nice to see something in action.

What language is this in?
FunkDaMonkMan is offline   Reply With Quote
Old 05-19-2005, 03:10 AM   #14
Constant Bitrate
 
ruairi's Avatar
 
Join Date: Jan 2005
Location: Spain
Posts: 165
ruairi is on a distinguished road
Quote: Originally Posted by CdRsKuLL
ok had a quick play.. seems to work fine for about 3 or 4 mins, then the main screen disappears and nothing happens, the only way to close it then is by taskbar manager.

OK, I should have documented the functionality, but it will take forever to write! The main window has a timeout, if you look in the settings.xml file there is a section saying: <activeTimeout>45</activeTimeout> Here this specifies how long the main window should be open and recognising commands. Once the timeout is reached it closes the window and stops recognising. You can set this to the number of seconds you want, if you set it to <activeTimeout>45</activeTimeout> then the window will not timeout and you need to press Hide or Exit, Exit closes the App completely, Hide closes the main window.

OK, you can close the App even if the main window is closed. Notice the transparent button on the top left and side that says "SpeakEasy VR". If you press on the SpeakEasy text then it opens the main windows and starts the recogniser again. If you press on the VR part then it EXITs the App completely. Also if you right click anywhere on the Speakeasy text it EXITs the App.

Quote:
Also.. 1st request :-) would it be possible to make it work like a multi remote control.. so say you are using freedrive.. you say freedrive once.. then any commands you wish, rather than having to say freedrive all the time.. like you would press dvd on the remote then all the keys are sent to the dvd.. then if you want to use roadrunner you say roadrunner, then all commands are sent to that app. ?

CDR, there is a LOCK command but I've left it out of the ini file to keep it simple for people at the start. Look in the vocab folder and open map.ini and add these lines, below.

"warning disbale ***" turns off one grouping complete so if you say "warning disbale free drive" then nothing from the free drive group will be recognised. All the other groups are enabled still. You can turn them off one by one if you wish. "warning reset ***" turns the specified grouping back on.

"warning lock ***" will lock the recogniser so it just recognises the group you specify. So "warning lock free drive" will mean only the free drive grouping will be recognised. There is one exception, the "lock reset" command which is used to turn the groups all on again. "lock reset" does the same things as the "Reset" button on the GUI.

CDR, the extra bit you want is to not have to say the prefix like "freedrive". This can be done, I'll add it to the next release.
Code:
#----------------------------------------------- [warning disable] map SE::map-disable Listen for Map commands music SE::music-disable Listen for Music commands playlist SE::playlist-disable Listen for playlist commands warning car SE::warning car-disable Listen for Music commands car SE::car-disable Listen for Music commands [warning reset] map SE::map-enable Listen for Map commands music SE::music-enable Listen for Music commands playlist SE::playlist-enable Listen for playlist commands warning car SE::warning car-enable Listen for Music commands car SE::car-enable Listen for Music commands [warning lock] map SE::map-lock Lock Map commands music SE::music-lock Lock Music commands playlist SE::playlist-lock Lock playlist commands warning car SE::warning car-lock Lock Warning car commands car SE::car-lock Lock car commands [lock] reset SE::reset-unlock Unlock Map commands #-----------------------------------------------

Quote:
Also it took me a while to figure out I needed to load the ini file.. could you load this as a default one on startup maybe ?

I presume you're talkign about the Vocab Editor. Yes I'll do that it is a good idea. I'll change the filename to default.ini and make it open in the Eidtor by default, if it exists. Thanks for that idea.

Quote:
this looks like its got loads of potential good work m8 :-)

It's got a long way to go, lots on the TODO list.

Last edited by ruairi; 05-19-2005 at 03:18 AM.
ruairi is offline   Reply With Quote
Old 05-19-2005, 03:17 AM   #15
Constant Bitrate
 
ruairi's Avatar
 
Join Date: Jan 2005
Location: Spain
Posts: 165
ruairi is on a distinguished road
Cheers FunkDaMonkMan, your Bruno application inspired me to get off my *** and write some code. The way you designed the vocab files was fantastic, it help me to see that you could make voice recognition very configurable.

Yep, the settings GUI is vile, I need to work on it.

It's all in C#.
ruairi is offline   Reply With Quote
Sponsored links
Advertisement
 
Advertisement
Reply

Bookmarks

Thread Tools
Display Modes

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off
Trackbacks are On
Pingbacks are On
Refbacks are Off


Similar Threads
Thread Thread Starter Forum Replies Last Post
Bruno Speech Recognition BETA v1.2 FunkDaMonkMan Bruno Speech Recognition 45 05-03-2005 02:03 PM
Voice recognition support smashr2k Centrafuse 1 12-06-2004 02:33 PM
Voice recognition using SAPI djScript Software & Software Development 17 09-30-2004 08:59 AM
Voice Recognition + Database Access Over modem?? az1324 Software & Software Development 1 04-09-2004 08:32 PM
voice recognition (sp?) blaine1605 General Hardware Discussion 57 02-04-2004 06:59 PM



All times are GMT -5. The time now is 10:50 PM.


Powered by vBulletin® Version 3.8.4
Copyright ©2000 - 2009, Jelsoft Enterprises Ltd.
Content Relevant URLs by vBSEO 3.3.2
Copyright © 1999 - 2008 Mp3Car.com Inc.Ad Management by RedTyger
Message Board Statistics