Pierre,

There is not much stopping you from experimenting on your own right now.

It helps if you are familiar with asterisk commands and at least bash scripts. AGI scripting a plus, but you can figure that out, it's all well documented.

This has been done with asterisk for at least 6-7 years.

I'm sure those folks at nervittles.com have some updated packages now-a-days.

A quick look shows   http://nerdvittles.com/?p=21703    so there is your start. Adapt from that.

As far as not triggering it outside of your intended system,

that can be accomplished using app_rpt's event management system,

a quick look at 'last keyed node' will give you the data to evaluate if the node that gave the attention keyword is one you want to allow the flow of voice commands and can/will prevent network falsifying.

The major hick-ups that I had was from all the dev's and hack's kept overloading the free use of dev tools and google and MS kept changing the criteria for how it worked. The more that were playing, the faster the changes came in. Much like voice.google has finally been shut down as a open interface in the end after frequent changes to eliminate those that were using it for unintended purposes.  Those changes were a bit slower since google had contracts for devices that worked from them. The same will probably happen to the voice assistant boxes in the end. I have seen so many hacks for them on the internet now. Enjoy and learn from the freebie while you can.

Personally, now, I don't have a interest in any of them that rely on external networks to do the task. But a STT/TTS engine run on a local server is not a uncomplicated task if it is to be accurate. And that's why google, MS, IBM and a few others have this pretty much wrapped up for now, but not forever. They did spend about 5+ years developing this and there was quite a battle over the talent to do it between MS and Google.

Anyway, I see you have the bug... really,  you should go for it ! It is fun. The more that are playing, the better the chances someone comes up with something really useful, not just novel.

...mike/kb8jnm


On 1/6/2019 11:08 AM, Pierre Martel wrote:
Thanks William for the feedback. 

I find your implementation on the IRLP controler to be a piece of art.. ;-)

Can I ask you what method did you used for the irlp controler? was it the original irlp software or did you used the irlp driver in app_rpt?

did you implement a way to prevent the AI to respond to request sent by a networked audio feed?

I am hyper excited by this and cant wait to test this. 

Pierre 
VE2PF





Le dim. 6 janv. 2019 à 08:53, William Franzin <wfranzin@gmail.com> a écrit :
Good morning,

We're also keen AllStarLink/app_rpt users/experimenters here in Winnipeg and Dan mentioned a discussion about the work I did on here, so thought I'd fill in the blanks. Also joined this list.

I started with Google Assistant and Amazon Alexa and really just wanted to control devices using voice, the "what's the weather" was just an added bonus, but all that requires internet.

I also liked the speed of running the assistant code in real-time, as you speak that's actually a stream to Google/Amazon so the results you get are immediate vs rec/upload/download/play.

For the majority of ham radio actual "needs" in voice control the Picovoice Rhino project speech-to-intent would do a great job. If you haven't check it out: https://github.com/Picovoice

Also watch their video: https://www.youtube.com/watch?v=WadKhfLyqTQ which I think is exactly what we'd want from a ham radio setup. Wakework "Hey Repeater" "Turn on ..". 

All of that great capability runs entirely on the device/server/reflector, no internet or web service call to Google/Amazon is needed. And it produces this simple output too: 

{
  "type": "espresso",
  "size": "small",
  "numberOfShots": "2",
  "sugar": "a lot",
  "milk": "some"
}

We should do this, my 2010 Ford Escape has had Microsoft Sync voice control and it's nothing new. Everything has voice control these days, and it actually works really well now.

The only challenge in ham is we need to come up with some standard commands so if you're visiting here you know the repeater has this capability and how to work it. 

If anything I'm just glad the videos I posted a while back got this topic going again. Certainly not the first person to poke around with voice - it's just really easy now to implement this.

Thanks to all the folks working on AllStarLink/app_rpt too. I just built a firmware image with AllStarLink for a Sierra Radio Systems CommServer board and it was apt-get-easy --let-me-drink-my-coffee-while-the-hard-work-gets-done ;)

Thanks,
William VE4VR
_______________________________________________
App_rpt-users mailing list
App_rpt-users@lists.allstarlink.org
http://lists.allstarlink.org/cgi-bin/mailman/listinfo/app_rpt-users

To unsubscribe from this list please visit http://lists.allstarlink.org/cgi-bin/mailman/listinfo/app_rpt-users and scroll down to the bottom of the page. Enter your email address and press the "Unsubscribe or edit options button"
You do not need a password to unsubscribe, you can do it via email confirmation. If you have trouble unsubscribing, please send a message to the list detailing the problem. 

_______________________________________________
App_rpt-users mailing list
App_rpt-users@lists.allstarlink.org
http://lists.allstarlink.org/cgi-bin/mailman/listinfo/app_rpt-users

To unsubscribe from this list please visit http://lists.allstarlink.org/cgi-bin/mailman/listinfo/app_rpt-users and scroll down to the bottom of the page. Enter your email address and press the "Unsubscribe or edit options button"
You do not need a password to unsubscribe, you can do it via email confirmation. If you have trouble unsubscribing, please send a message to the list detailing the problem.