[REL] sh4speech - voice command for SH4

[minsc_tdp]

shSpeech - Voice Command for Silent Hunter 4 by minsc_tdp

sh4speech is a voice command program for Silent Hunter 4, but could be adapted to other games (and has been adapted to SH3 now!) It currently supports everything the game can do, allowing you to issue all orders completely hands-free, which frees up your mouse to only manipulate the cameras and periscope, map, and other things that traditionally did not involve spoken orders.

It is extremely quick, responsive, reliable, and the recognition is great if you follow the readme and spend a few minutes training your speech system and if you adjust your microphone often. The first time you hear someone bark "Yes sir!" in response to an order you barked yourself at your crew, your whole SH experience will change forever!

Downloads
v2.55 ***LATEST GOOD VERSION*** aka "DON'T STOP BELIEVIN' RELEASE
Download page: http://knepfler.com/shSpeech

Silent Hunter 3
TomcatTwo modded this to work with Silent Hunter 3. To be honest, he put my work to shame! He added a lot of commands, even in German, and his documentation and immersion level is outstanding! Check it out here. I'm glad to have contributed the core technology to this awesome project. Congratulations TomcatTwo on an awesome release!

Latest Changes
June 29, 2016 (2.55 aka "DON'T STOP BELIEVIN RELEASE") - Added tmo 2.5 files by razark
Mar 01 2008 (2.54) - Fixed resolution scaling problems for TomcatTwo's SH3 mod (dials should work better in this one vs. 2.53)
Mar 01 2008 (2.53) - Fixed resolution scaling problems for TomcatTwo's SH3 mod
Feb 23 2008 (2.52) - Added "Pause Recognition" and "Resume Recognition" commands with underlying code support
Feb 19 2008 (2.51) - Added additional launch BAT files for left-handed users with underlying code support. Untested.
Feb 13 2008 (2.50) - Important adjustments made to location of voice_commands.csv and press_to_talk.csv files. If you have customized your CSV files, you must read the ChangeLog! Other minor adjustments nobody will really notice.
Feb 9 2008 (2.25) - Fixes a problem where extra spaces at the end of voice commands would cause them to not work
Feb 5 2008 (2.24) - Adds support for multiple "hold keys", so you can do CTRL-SHIFT-ALT-X instead of being limited to only one, where you could only do CTRL-X or SHIFT-X or ALT-X. See the ChangeLog for full explanation.
See the full changelog for a complete history of changes.

Docs
Readme
ChangeLog
Voice Command Reference Card

Videos
http://knepfler.com/shSpeech

URLs
Older Thread: http://www.subsim.com/radioroom/showthread.php?t=119039

[corleonedk]

I take my hat of for you m8,its late now but will test this tommorow..Well done

[minsc_tdp]

I've been playing with it for more than an hour or so. DAMN is it fun! Hasn't misinterpreted a single command. Did a convoy kamikaze mission to stress it out. Only a very small number of commands went unheard, such as "hard to port" for some reason (probably due to the rough T sounds), but usually only when stuff on my boat was exploding, which I find very realistic! The recognition and response is very quick. I can't wait to set up shooting solutions with it. I'm playing with a nice mic about 1.5 feet from my mouth on the desk, and it works great even with 5.1 sound blaring throughout the room and my brother's stereo cranked in the next room.

[panthercules]

Man - that was quick work - I can't wait to plow into this. I got my new PC built and so far so good on it (doubled fps on my SH4 benchmark ), but have run into a little trouble on one of the other 3 I'm upgrading so it will still probably be tomorrow night or later before I can get back and test this out. Early reports from the posts above are certainly encouraging.

Thanks for hanging with this

[minsc_tdp]

I've updated some critical install information to help you get things running. Let me know if there's any problems! God I'm so drunk right now I can't believe I'm posting this. The world is a total blur.

UPDATE: Now sober, I've tweaked the install instructions again and matched up the readme.txt instructions in the download with the instructions in the thread here.

[panthercules]

Got some time while one of the other PCs is installing windows and was going to start playing around with this, but I'm confused by the install instructions. The first post above states:

2. Start > run > \sh4speech\install.bat. This will start the install for:
ActivePerl
...

I've downloaded ActivePerl and Active Python from the links you provided, but I haven't installed them yet (I'd already downloaded and installed the MS SDK thing a few days ago). Does the statement above mean that your bat file installs ActivePerl and/or ActivePython, or do I need to have installed ActivePerl and Active Python from the downloads first before I start running your install.bat file?

[g_g_h]

Hi guys,
I know that some of you succeeded to run it with Vista.

I read the readme but it is not so clear. It tells me to instal MS SDK - which is not requred with Vista. So I just downloaded sh4speech v. 2.54. I unpacked it in c:\shspeech folder. I ran Vista speech recogn. tool, then I ran sh4speech stock. bat as I got one. I see in the cmd window that my commands are recognized but they are not done in the game.
In some threads I'v seen some info about the perl and phyton. Do i need to install is as well? readme do not mention it.

[raymond6751]

Originally Posted by minsc_tdp

I've been playing with it for more than an hour or so. DAMN is it fun! Hasn't misinterpreted a single command. Did a convoy kamikaze mission to stress it out. Only a very small number of commands went unheard, such as "hard to port" for some reason (probably due to the rough T sounds), but usually only when stuff on my boat was exploding, which I find very realistic! The recognition and response is very quick. I can't wait to set up shooting solutions with it. I'm playing with a nice mic about 1.5 feet from my mouth on the desk, and it works great even with 5.1 sound blaring throughout the room and my brother's stereo cranked in the next room.

Hmmm. I stopped using previous voice cmd software because extraneous sounds would cause problems. I wonder if the results above were due to a good mic or the software? Anyone else have same results as above?

[Jaeger]

hi minsc,

i hope you can help me using the speech engine for sh4 with a german vista. i installed the german language pack on my english vista ultimate, now my running system is completly german. the speech recognition engine is running fine in vista (it understands most of my german orders, the language is set to german of course) but when using your programm, i have got some problems. i changed some commands in the voice_commands.csv to german words (for ex. Angriffssehrrohr for periscope), but it doesnt understand them. the vista recognition engine is running in the background. what is the key? where is my problem? i think it should be possible to use your program in german language, isnt it?

edit: some words are recognised every time and i can read them in the vista applet too, but others never are understood, though they are in the voice_commands.csv list. an example: "feuer" is recognised every time, "seekarte" is never recognised. in dictat mode (in notepad for ex.), these words are well understood... why not in sh4speech?

[Jaeger]

bump!

ary there any members here, who tried to use the speech engine in another language than english?

[Snakeeyes]

Hey Minsc,

I'm new to VAC. How do I install your SHIV profile?

[minsc_tdp]

Originally Posted by Snakeeyes

Hey Minsc,I'm new to VAC. How do I install your SHIV profile?

I'm new to VAC too, since I don't know what VAC means.

What profile? If you're talking about keyboard configuration and command bar setup, this sh4speech is designed for an unmodified SH4 default configuration.

[panthercules]

Well, just running the new version (without using the install.bat since I still had all the version 1.0 ancillary programs already installed) seems to have worked just fine. The single-window, more verbose test mode seemed to work well, though perhaps it would be nice to be able to have the verbose mode be a selectable/switch type thing so you would only get all that extra stuff if you're having issues and want to debug them - it was a bit hard/time consuming to wade through all the extra output just to confirm that the commands were being recognized correctly when I was just trying to do a quick run through of all my commands to make sure they worked.

Haven't had a chance to try this out in game yet, but the tube selection/door opening and closing mechanism worked very well in test mode. One thing that threw me briefly was the lack of any output in test mode in response to the mouse/command bar voice commands I tried - it finally dawned on me that I probably wasn't going to get results in test mode from asking for the fuel, CO2 and battery status since I wasn't in game, but it would have been helpful if there was some sort of output that would at least acknowledge that the command had been recognized even though the output wasn't a key stroke. Small thing - just something to think about.

Also - I noticed that one of the command bar items (sets of commands) was labeled "oxygen" and had associated voice commands about running out of air to breathe - IIRC however, shouldn't that actually be referring to the compressed air level indicator, and not the breathable air levels (which is really a function of the CO2 indicator in an inverse sense)?

[minsc_tdp]

Originally Posted by panthercules

it would be nice to be able to have the verbose mode be a selectable/switch type thing so you would only get all that extra stuff if you're having issues and want to debug them - it was a bit hard/time consuming to wade through all the extra output

True, it's a lot, but I try to indent everything that's not an actual spoken command so they show up on the left. But I probably should add a debug mode/logger or something for all that extra.

One thing that threw me briefly was the lack of any output in test mode in response to the mouse/command bar voice commands I tried - it finally dawned on me that I probably wasn't going to get results in test mode from asking for the fuel, CO2 [...] but it would have been helpful if there was some sort of output

In test mode, you should see it move the mouse, but not click the mouse button. That's the test feedback, I just avoid clicking since you're probably in windows and I don't want to accidentally delete all your porn or upload your credit card number or something.

Also - I noticed that one of the command bar items (sets of commands) was labeled "oxygen" and had associated voice commands about running out of air to breathe - IIRC however, shouldn't that actually be referring to the compressed air level indicator, and not the breathable air levels (which is really a function of the CO2 indicator in an inverse sense)?

That was a joke more than anything I thought O2 was breathable but you're probably right, CO2 is probably the only thing related to crew breathing and O2 should be renamed to compressed air in all the voice commands.

[panthercules]

Originally Posted by minsc_tdp

In test mode, you should see it move the mouse, but not click the mouse button. That's the test feedback, I just avoid clicking since you're probably in windows and I don't want to accidentally delete all your porn or upload your credit card number or something.

LOL - never mind - apparently, somewhere along the way in merging my old version 1.0 .csv files with the new ones, I must have failed to save the version that had the fuel/CO2/battery button bar commands, which explains why I wasn't getting any feedback in test mode. Added them back in to my voice_commands.csv and it worked like a charm in test mode.

Originally Posted by minsc_tdp

True, it's a lot, but I try to indent everything that's not an actual spoken command so they show up on the left. But I probably should add a debug mode/logger or something for all that extra.

I think the reason the indentation doesn't help as much as it could is that for some reason I can't seem to maximize/resize the command prompt window that the test mode is running in to make it large enough to keep some of the longer text from wrapping around to the left margin again, which clutters the screen a bit during the test mode. Obviously, not worth spending any real time on, since it does seem to be working in any event.

Now to get out to sea to try this out for real - keep up the great work