asterisk users - Aug 2010 - Opensource Speech recognition for Asterisk

Hi Everyone,

Has anyone got any opensource speech recognition software to work with
Asterisk? Please only list WORKING ones. Not the "theoretically"
should work
ones!

Thanks
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
http://lists.digium.com/pipermail/asterisk-users/attachments/20100821/4d11d6c0/attachment.htm

I yet have to see ANY working speech recognition software, free or not. This
technology is nothing more than a joke so far, not practical at any level.
As for free, there is nothing decent.

Zeeshan A Zakaria

--
www.ilovetovoip.com

On 2010-08-21 4:31 PM, "bruce bruce" <bruceb444 at gmail.com>
wrote:

Hi Everyone,

Has anyone got any opensource speech recognition software to work with
Asterisk? Please only list WORKING ones. Not the "theoretically"
should work
ones!

Thanks

--
_____________________________________________________________________
-- Bandwidth and Colocation Provided by http://www.api-digital.com --
New to Asterisk? Join us for a live introductory webinar every Thurs:
              http://www.asterisk.org/hello

asterisk-users mailing list
To UNSUBSCRIBE or update options visit:
  http://lists.digium.com/mailman/listinfo/asterisk-users
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
http://lists.digium.com/pipermail/asterisk-users/attachments/20100821/b4b5fc0f/attachment.htm

On Sat, Aug 21, 2010 at 6:21 PM, Zeeshan Zakaria <zishanov at gmail.com>
wrote:
> I yet have to see ANY working speech recognition software, free or not.
This
> technology is nothing more than a joke so far, not practical at any level.
> As for free, there is nothing decent.
>
I disagree, while not Open Source like the OP requested, both Nuance
and Microsoft Speech Server are nothing to laugh at.

-- 
Paul Belanger | dCAP
Polybeacon | Consultant
Jabber: paul.belanger at polybeacon.com | IRC: pabelanger (Freenode)
blog.polybeacon.com

Then may be these big multi-billion dollar corporations should use one of
them, with whom we all deal regarding various services, and who put us
through these voice recognition time-wasting activity in a hope that the
poor caller will eventually give up, or will wait painfully long until one
of their agent will get time to attend call in person.

Your experience could be different and better then most, and you have
certainly complete right of your own opinion.

Zeeshan A Zakaria

--
www.ilovetovoip.com

On 2010-08-21 6:57 PM, "Paul Belanger" <paul.belanger at
polybeacon.com> wrote:

On Sat, Aug 21, 2010 at 6:21 PM, Zeeshan Zakaria <zishanov at gmail.com>
wrote:
> I yet have to see ANY...
I disagree, while not Open Source like the OP requested, both Nuance
and Microsoft Speech Server are nothing to laugh at.

--
Paul Belanger | dCAP
Polybeacon | Consultant
Jabber: paul.belanger at polybeacon.com | IRC: pabelanger (Freenode)
blog.polybeacon.com

--

_____________________________________________________________________
-- Bandwidth and Colocation Pr...
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
http://lists.digium.com/pipermail/asterisk-users/attachments/20100821/25ced34f/attachment.htm

> Hi Everyone,
> 
> Has anyone got any opensource speech recognition software to work with
> Asterisk? Please only list WORKING ones. Not the "theoretically"
should work
> ones!
Hi

I definitely suggest you to try CMU Sphinx connector for Asterisk. You
can find all required information here

http://scribblej.com/svn/

If you need any help with setup, just ask.

-- 
Nexiwave - Speech Indexing Solution For Call Centers
http://nexiwave.com

-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 198 bytes
Desc: This is a digitally signed message part
Url :
http://lists.digium.com/pipermail/asterisk-users/attachments/20100822/decca13f/attachment.pgp

Thanks guys. A lot of info here :-)

I am wondering if anyone followed this and it was working for them:

http://scribblej.com/svn/

???

I am not looking for anything fancy. The basic "yes", "no",
dialing a
number, asking for agent, etc...out of which probably the hardest is a 10
digit number to be asked to be dialed.

Thanks


On Sun, Aug 22, 2010 at 2:30 AM, Nickolay V. Shmyrev
<nshmyrev at nexiwave.com>wrote:
> > Hi Everyone,
> >
> > Has anyone got any opensource speech recognition software to work with
> > Asterisk? Please only list WORKING ones. Not the
"theoretically" should
> work
> > ones!
>
> Hi
>
> I definitely suggest you to try CMU Sphinx connector for Asterisk. You
> can find all required information here
>
> http://scribblej.com/svn/
>
> If you need any help with setup, just ask.
>
> --
> Nexiwave - Speech Indexing Solution For Call Centers
> http://nexiwave.com
>
>
> --
> _____________________________________________________________________
> -- Bandwidth and Colocation Provided by http://www.api-digital.com --
> New to Asterisk? Join us for a live introductory webinar every Thurs:
>               http://www.asterisk.org/hello
>
> asterisk-users mailing list
> To UNSUBSCRIBE or update options visit:
>   http://lists.digium.com/mailman/listinfo/asterisk-users
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
http://lists.digium.com/pipermail/asterisk-users/attachments/20100822/8d872a13/attachment.htm

On Sat, Aug 21, 2010 at 7:09 PM, Zeeshan Zakaria <zishanov at gmail.com>
wrote:
> Your experience could be different and better then most, and you have
> certainly complete right of your own opinion.
>
Speech recognition is only as effective as your grammars and they are
never 100%. The require lots tuning and analyzing to be effective.  My
clients I works with simply believe once the IVR is developed and
installed, the work end there; This is never the case.

We actively consult with a Speech Linguist when are in the tuning
phase of the grammars.  Countless hours listening to recorded calls,
rebuilding grammars, in an attempt to increase accuracy.  Lots of hard
work, but when you actively improve grammars, recognition rates
increase.

-- 
Paul Belanger | dCAP
Polybeacon | Consultant
Jabber: paul.belanger at polybeacon.com | IRC: pabelanger (Freenode)
blog.polybeacon.com

> Thanks guys. A lot of info here :-)
>
> I am wondering if anyone followed this and it was working for them:
>
> http://scribblej.com/svn/
>
> ???
Hello Bruce

We successfully deployed it and now saving thousands on commercial ASR
ports. It seems users are rather happy with it. The recognition seems
pretty accurate. Of course it has it's own limitations but so any
other technology. It will not hurt if some of your users will benefit
from ASR.
> I am not looking for anything fancy. The basic "yes",
"no", dialing a
> number, asking for agent, etc...out of which probably the hardest is a 10
> digit number to be asked to be dialed.
Yes, that should work. It also supports JSGF grammars, so you should
be able to recognize digit strings easily.

And if you want something serious, there are at least two open source products
providing ASR over standard MRCP protocol. They also use CMUSphinx, so
provide the same accuracy

Zanzibar http://www.spokentech.org/writing-speechlets.html
Cairo http://www.speechforge.org/

Though Cairo is a bit dated.