There's not really an easy way to do this out of the box.  The FS core provides all the low-level functions necessary for doing ASR, but nothing higher level for interpreting results, handling barge-in, starting input-timers, etc.

I solved this issue with a custom dialplan APP.  I know of another other dev that used event socket and the playback/detect_speech dialplan APPs.  Looking at the scripts/javascript/js_modules/SpeechTools.jm source, you can see that anthm solved it a different way.



On Mon, Sep 5, 2011 at 3:02 AM, Glen Ganderton <Glen.Ganderton@premier.com.au> wrote:

Hi Guys,

 

What i am trying to do is configure an IVR using freeswitch and Nuance 5.1.5 to perform speech recognition. I have installed the latest

release of freeswitch on my CentOS system, I have also enabled and configured the unimrcp module. I could find lots of information to

configure the unimrcp module but there is no documentation on how to create IVR menu's using this module with Nuance. I have used the

demo pizza IVR with the pocketsphinx module and I keep getting refered to this but it's no help as I want to use Nuance for ASR. Any

help on how to configure this would be great, specifically:

 

* How to I call the IVR script from the dialplan

* What language/s can I code the IVR in and can you please provide a basic sample of how this is done with Nuance.

 

Thank you in advance

 

--Glen



FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users
UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org