All;
Since I have interest in providing the capability for callers to speak
the department, person or number they wish to call, as well as other IVR
scenarios, I have been reviewing much of this lists email archives and
searching the web for open source voice recognition that will work with
the Asterisk PBX.
What I am trying to determine, is what will it take to get it working on
Asterisk? How much effort and cost?
So far I have uncovered references to the following:
1) VoiceXML standards, and forums
2) OpenVXI - which supports VoiceXML, simulated speech,
telephony
3) PublicVoiceXML
4) Sphinx - a Carnegie Mellon University Speech recognition
project funded by DARPA
>From what I can tell, I feel I am uncovering the tip of the ice berg and
this may not be trivial. But it seems that the Voice recognition
application, once developed, would have to be linked via an AGI to the
asterisk dial plan.
Has anyone gotten Voice recognition working with Asterisk? Last I saw, a
few were attempting to apply Sphinx back in the December and April time
frame. Any shared successes, progress or direction on Sphinx or any
other VR app would be appreciated before I start down this road.
Thanks,
Mike Meyer
On Fri, 2004-08-27 at 13:26, Mike Meyer wrote:>Mike, I have been mulling similar ideas for some time. I've turned up the same projects you have.> >From what I can tell, I feel I am uncovering the tip of the ice berg and > this may not be trivial.I've pretty much got the same feeling based on my research. I don't think this is a trivial problem to solve.> But it seems that the Voice recognition > application, once developed, would have to be linked via an AGI to the > asterisk dial plan.I think this is accurate. You would use either AGI or a native Asterisk module to connect the pieces.> Has anyone gotten Voice recognition working with Asterisk? Last I saw, a > few were attempting to apply Sphinx back in the December and April time > frame. Any shared successes, progress or direction on Sphinx or any > other VR app would be appreciated before I start down this road.I have nothing working at this point, just some ideas and a plan to explore further. As soon as I have "free" time I'm hoping to explore some of my ideas on my * system. I certainly would be happy to hear others' experiences on this mail list. -joe -- Innovation Software Group, LLC - http://www.innovationsw.com Custom Internet and Computer Solutions Linux, UNIX, Java Training
Raul Elizondo (wizardteam)
2004-Aug-27 11:23 UTC
[Asterisk-Users] AGI dtmf problems (with x-lite)
Hi guys, May be this is a subject already disscused some where before, but i cant find a solution. By using x-lite, i can dial in menus, or even in voicemail during the process of any of both. But when i run my own AGI (using tcl), it does not detect DTMF when "GET DATA" function. I got no more than a month that i downloaded asterisk via cvs, is this problem already fixed in the mean time? or is there something else i have to set in my AGI? Regards, -=Raul=-
I dumped about 2 weeks of my life into doing just batch speech-to-text using
Sphinx2. After doing all sorts of custom configurations to the Sphinx batch
run-time parameters and using a very limited vocabulary I was able to
recognize about 95% of the phrases that were uttered in 4000 random snippets
of conversations that I recorded from Asterisk.
I was never able to get real-time conversion working in any reliable form
over phone quality audio, and due to the processor and memory requirements
it would be rather limiting to try using it on a busy IVR system. Sphinx
runs best the more RAM it has(suggested minimum 256MB of RAM) and it is very
much a processor hog.
I would be very interested to hear if anyone has any experiences with IBM's
viavoice product in a real-time capacity(even though I understand it is
quite expensive for a multi-stream license).
In the end Sphinx2 worked well enough for what I needed to do(batch
processing of phrases in a limited vocabulary), but nowhere near well enough
to try using it real-time in any way. Sphinx4 promises to be much better at
conversion, but it is very much still beta at this time.
Hope this helps.
MATT---
-----Original Message-----
From: Mike Meyer [mailto:mjmeyer@gendesign.com]
Sent: Friday, August 27, 2004 1:27 PM
To: Asterisk Users Group
Subject: [Asterisk-Users] Speech Recognition and Asterisk
All;
Since I have interest in providing the capability for callers to
speak
the department, person or number they wish to call, as well as other IVR
scenarios, I have been reviewing much of this lists email archives and
searching the web for open source voice recognition that will work with
the Asterisk PBX.
What I am trying to determine, is what will it take to get it working on
Asterisk? How much effort and cost?
So far I have uncovered references to the following:
1) VoiceXML standards, and forums
2) OpenVXI - which supports VoiceXML, simulated speech,
telephony
3) PublicVoiceXML
4) Sphinx - a Carnegie Mellon University Speech recognition
project funded by DARPA
>From what I can tell, I feel I am uncovering the tip of the ice berg and
this may not be trivial. But it seems that the Voice recognition
application, once developed, would have to be linked via an AGI to the
asterisk dial plan.
Has anyone gotten Voice recognition working with Asterisk? Last I saw, a
few were attempting to apply Sphinx back in the December and April time
frame. Any shared successes, progress or direction on Sphinx or any
other VR app would be appreciated before I start down this road.
Thanks,
Mike Meyer
_______________________________________________
Asterisk-Users mailing list
Asterisk-Users@lists.digium.com
http://lists.digium.com/mailman/listinfo/asterisk-users
To UNSUBSCRIBE or update options visit:
http://lists.digium.com/mailman/listinfo/asterisk-users
On Fri, 2004-08-27 at 12:26, Mike Meyer wrote:> All; > > Since I have interest in providing the capability for callers to speak > the department, person or number they wish to call, as well as other IVR > scenarios, I have been reviewing much of this lists email archives and > searching the web for open source voice recognition that will work with > the Asterisk PBX.This is a very hard problem in total, but parts of it are not too difficult. Voice recognition with no training is hard. IT is hard enough to be the very reason it isn't widly deployed now. What is deployed now is usually limited to small vocabularies. Sounds like your request might be able to handle that. For a fairly simple hookup, you could try to write an application for AGI that records a prompt with either a timeout or a silence threshold. Then send that audio off to a application like sphynx with a small vocabulary list to match against. It should return to you a fairly decent idea of what was said. Do remember though that accents might throw it off so be prepared for other options of input. Last I tried, sphynx wasn't too hard to install, but was a pain to use. I would suggest small recordings over EAGI as you can send audio to sphynx in small chunks and with a vocabulary list of expected terms. -- Steven Critchfield <critch@basesys.com>