VoIP Mailing List Archives
Mailing list archives for the VoIP community |
|
View previous topic :: View next topic |
Author |
Message |
anthony.minessale at g... Guest
|
Posted: Tue Jan 13, 2009 12:17 pm Post subject: [Freeswitch-users] FreeSWITCH, MRCP and Perl |
|
|
Maybe Arsen can chime in. He is the author of unimrcp and the previous openmrcp.
I would assume it would be a few k to hire some developers to work on the module.
The new library is working so it should be straightforward. I am willing to help answer questions
for whomever wants to code it and we will even try to get the module started but we need to add
it to a very large todo list.
On Tue, Jan 13, 2009 at 10:18 AM, Paul Herring <paulh@instruments.com (paulh@instruments.com)> wrote:
Quote: | What would it take to put a budget together to for this project?
Date: Tue, 13 Jan 2009 01:55:36 -0500
From: mszlazak@aol.com (mszlazak@aol.com)
Subject: Re: [Freeswitch-users] FreeSWITCH, MRCP and Perl
To: freeswitch-users@lists.freeswitch.org (freeswitch-users@lists.freeswitch.org)
Message-ID: <8CB436312A08329-80C-1B5D@MBLK-M24.sysops.aol.com (8CB436312A08329-80C-1B5D@MBLK-M24.sysops.aol.com)>
Content-Type: text/plain; charset="us-ascii"
"My god" I would LOVE it if this is really the case and would praise
pocketsphinx (PS) and FS to no end. But my experience has been different.
First, I tried the pizza demo with a soft phone and later by outside phone
calls to my Linksys 3102 pstn-to-voip gateway.
Second, I tried these two set-ups again but with Voxeo's Prophecy ASR.
Both are as is and by this I mean there was no training of PocketSphinx just
running the pizza demo and with Prophecy there is no training because it
can't be trained.
Prophecy is quite good but the FS/Pocketsphinx pizza demo isn't and I
couldn't use it at a pizza join. Also, I get a much better experience when
calling LumenVox and trying their pizza demo.
Now, maybe Prophecy is the type of asr that doesn't require hours of
training to make it speaker independent. I know that the Sphinx family are
the types of ASR that do need this.
So, if there is some settings for adaptation of Pocketsphinx for speaker
independence then are they turned on?
?
How many hours of calls to a business should an owner expect before
PocketSphinx gets good enough not to scare customers away?
If there are many hours needed then I could see using another ASR in the
mean time, recording their calls and feeding the audio to Pocketsphinx for
training, then switching to Pocketspinx once it's "tuned up." At least this
way a business doesn't have to deal with a "virgin" pocketsphinx.
Mark
--
This message has been scanned for viruses and
dangerous content by MailScanner, and is
believed to be clean.
_______________________________________________
Freeswitch-users mailing list
Freeswitch-users@lists.freeswitch.org (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
|
--
Anthony Minessale II
FreeSWITCH http://www.freeswitch.org/
ClueCon http://www.cluecon.com/
AIM: anthm
MSN:anthony_minessale@hotmail.com ([email]MSN%3Aanthony_minessale@hotmail.com[/email])
GTALK/JABBER/PAYPAL:anthony.minessale@gmail.com ([email]PAYPAL%3Aanthony.minessale@gmail.com[/email])
IRC: irc.freenode.net #freeswitch
FreeSWITCH Developer Conference
sip:888@conference.freeswitch.org ([email]sip%3A888@conference.freeswitch.org[/email])
iax:guest@conference.freeswitch.org/888
googletalk:conf+888@conference.freeswitch.org ([email]googletalk%3Aconf%2B888@conference.freeswitch.org[/email])
pstn:213-799-1400 |
|
Back to top |
|
|
mszlazak at aol.com Guest
|
Posted: Tue Jan 13, 2009 1:17 pm Post subject: [Freeswitch-users] FreeSWITCH, MRCP and Perl |
|
|
Apparently you did. I was responding to comments/claims of another poster by relating my experiences and wishing that PS in FS would preform better.
-----Original Message-----
From: Anthony Minessale <anthony.minessale@gmail.com>
To: freeswitch-users@lists.freeswitch.org
Sent: Tue, 13 Jan 2009 8:58 am
Subject: Re: [Freeswitch-users] FreeSWITCH, MRCP and Perl
I'm missing something, What is your point exactly?
I *just* explained that we want to support unimrcp so you can use Prophecy if you wish so we get it, there is no need to continue to complain. I tried to tell you that we are short on time and we are trying our best.
We had openmrcp and the devloper discontinued the project. Now we need to get rid of it and switch to unimrcp.
If you recall, you called us for consulting, then spent an hour on the phone gathering free information then proceeded to get all kinds of free help on this list using the free software we have made available to you. It's great that Prophecy is the only place you want to spend any money and I encourage you to do so we can connect you with Voxeo any time. But what else exactly do you want from us?
You may want to factor in that your limited experience and particular requirements contribute to your trouble setting everything up so clearly the pocketsphinx route is not for you. (You are only the 2nd person to try it on windows for instance)
I keep reading all of your emails and I am trying to understand exactly what you want from us.
On Tue, Jan 13, 2009 at 12:55 AM, <mszlazak@aol.com (mszlazak@aol.com)> wrote:
Quote: | "My god" I would LOVE it if this is really the case and would praise pocketsphinx (PS) and FS to no end. But my experience has been different.
First, I tried the pizza demo with a soft phone and later by outside phone calls to my Linksys 3102 pstn-to-voip gateway.
Second, I tried these two set-ups again but with Voxeo's Prophecy ASR.
Both are as is and by this I mean there was no training of PocketSphinx just running the pizza demo and with Prophecy there is no training because it can't be trained.
Prophecy is quite good but the FS/Pocketsphinx pizza demo isn't and I couldn't use it at a pizza join. Also, I get a much better experience when calling LumenVox and trying their pizza demo.
Now, maybe Prophecy is the type of asr that doesn't require hours of training to make it speaker independent. I know that the Sphinx family are the types of ASR that do need this.
So, if there is some settings for adaptation of Pocketsphinx for speaker independence then are they turned on?
How many hours of calls to a business should an owner expect before PocketSphinx gets good enough not to scare customers away?
If there are many hours needed then I could see using another ASR in the mean time, recording their calls and feeding the audio to Pocketsphinx for training, then switching to Pocketspinx once it's "tuned up." At least this way a business doesn't have to deal with a "virgin" pocketsphinx.
Mark
-----Original Message-----
From: Brian West <brian@freeswitch.org (brian@freeswitch.org)>
To: freeswitch-users@lists.freeswitch.org (freeswitch-users@lists.freeswitch.org)
Sent: Mon, 12 Jan 2009 3:21 pm
Subject: Re: [Freeswitch-users] FreeSWITCH, MRCP and Perl
Quote: | Maybe for NON english speakers it doesn't do well but for my tests and
needs it does excellent. Sphinx isn't ready thats for sure.. but
PocketSphinx does great.
I have PocketSphinx doing voice dial by name directory on very common
and simple names. If you adapt it it can get much better. But have
you called AT&T lately? I have no idea what they use but OMG it
sucks... you say "NO" it doesn't understand you.. you say your account
number .. it doesn't understand you... you scream curse words at it
and it will take you to an agent so they can get you to the right
place. Its aweful. Pocketsphinx has performed better than that on my
testing.
/b
On Jan 12, 2009, at 5:09 PM, mszlazak@aol.com (mszlazak@aol.com) wrote:
Quote: | That's not the opinion of Nickolay S. from the Sphinx forums. He
|
Quote: | didn't think it was telephony ready but you implied something
|
Quote: | similar in a past email. Also, I got a similar impression with the
|
Quote: | pizza demo as it came with FS. Instead I tried Voxeo's Prophecy as
|
Quote: | per your recommendation and found it worked better. As I understand
|
Quote: | it, pocketsphinx and sphinx (3 & 4) are very good but need adapting
|
Quote: | and training for there various uses.
|
Quote: | So, why bother with LumenVox, Voxeo, Nuance, etc if one could get
|
Quote: | pocketsphinx working better since it's already integrated with FS?
|
_______________________________________________
Freeswitch-users mailing list
Freeswitch-users@lists.freeswitch.org (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
|
A Good Credit Score is 700 or Above. See yours in just 2 easy steps!
_______________________________________________
Freeswitch-users mailing list
Freeswitch-users@lists.freeswitch.org (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
|
--
Anthony Minessale II
FreeSWITCH http://www.freeswitch.org/
ClueCon http://www.cluecon.com/
AIM: anthm
MSN:anthony_minessale@hotmail.com ([email]MSN%3Aanthony_minessale@hotmail.com[/email])
GTALK/JABBER/PAYPAL:anthony.minessale@gmail.com ([email]PAYPAL%3Aanthony.minessale@gmail.com[/email])
IRC: irc.freenode.net #freeswitch
FreeSWITCH Developer Conference
sip:888@conference.freeswitch.org ([email]sip%3A888@conference.freeswitch.org[/email])
iax:guest@conference.freeswitch.org/888
googletalk:conf+888@conference.freeswitch.org ([email]googletalk%3Aconf%2B888@conference.freeswitch.org[/email])
pstn:213-799-1400
A Good Credit Score is 700 or Above. See yours in just 2 easy steps! |
|
Back to top |
|
|
mszlazak at aol.com Guest
|
Posted: Tue Jan 13, 2009 1:38 pm Post subject: [Freeswitch-users] FreeSWITCH, MRCP and Perl |
|
|
Hi Paul,
If you mean fixing up pocketsphinx (ps) for telephony instead of or in addition to working on unimrcp then this is the site of the person who created ps and he may have some advice.
http://www.cs.cmu.edu/~dhuggins/
Also, this was a post from the sphinx forums for adapting pocketsphinx for telephony.
http://sourceforge.net/forum/message.php?msg_id=5621913
I don't know how accurate it is but if accurate then here is that post to give you some of the issues involved:
-----------------
Well, there are issues in both the decoder and the interface with the
telephony application.
First about the decoder, pocketsphinx right now is the most supported
and most feature-reach decoder of the family, but in general it's still
oriented on the embedded devices. For telephony applications you
probably need to extend it a lot. The features that are currently
missing are probably:
* Out-of-box support for multiple recognizers (probably more a freeswitch
issue and a model training issue, for example we have no free
male/female model).
* Speaker clustering.
* Automatic VTLN estimation from pitch (This looks simple).
* Good endpointer.
* Discriminative training support in SphinxTrain (Huge task).
* Good and clean support for a garbage model to be able to filter out
out of grammar words.
* Embedded RASTA extraction and RASTA model training.
* Advanced features extraction
Another issue is dialog tracking and understanding. CMU folks are doing
work on dialog systems, for example Raven is available
http://www.ravenclaw-olympus.org/systems_overview.html
It would be worth to look on it and try to integrate it into
freepbx. Decoder will need to support combined language model. As well
as you'll need a component for postprocessing. The postprocessing includes
disfluency removal, text normalization, text boundary detection. Integration
with nltk probably useful for sense extraction.
If you need more details on any of the above, feel free to ask.
-------------------
-----Original Message-----
From: Paul Herring <paulh@instruments.com>
To: freeswitch-users@lists.freeswitch.org
Sent: Tue, 13 Jan 2009 8:18 am
Subject: [Freeswitch-users] FreeSWITCH, MRCP and Perl
Quote: | What would it take to put a budget together to for this project?
Date: Tue, 13 Jan 2009 01:55:36 -0500
From: mszlazak@aol.com (mszlazak@aol.com)
Subject: Re: [Freeswitch-users] FreeSWITCH, MRCP and Perl
To: freeswitch-users@lists.freeswitch.org (freeswitch-users@lists.freeswitch.org)
Message-ID: <8CB436312A08329-80C-1B5D@MBLK-M24.sysops.aol.com (8CB436312A08329-80C-1B5D@MBLK-M24.sysops.aol.com)>
Content-Type: text/plain; charset="us-ascii"
"My god" I would LOVE it if this is really the case and would praise
pocketsphinx (PS) and FS to no end. But my experience has been different.
First, I tried the pizza demo with a soft phone and later by outside phone
calls to my Linksys 3102 pstn-to-voip gateway.
Second, I tried these two set-ups again but with Voxeo's Prophecy ASR.
Both are as is and by this I mean there was no training of PocketSphinx just
running the pizza demo and with Prophecy there is no training because it
can't be trained.
Prophecy is quite good but the FS/Pocketsphinx pizza demo isn't and I
couldn't use it at a pizza join. Also, I get a much better experience when
calling LumenVox and trying their pizza demo.
Now, maybe Prophecy is the type of asr that doesn't require hours of
training to make it speaker independent. I know that the Sphinx family are
the types of ASR that do need this.
So, if there is some settings for adaptation of Pocketsphinx for speaker
independence then are they turned on?
?
How many hours of calls to a business should an owner expect before
PocketSphinx gets good enough not to scare customers away?
If there are many hours needed then I could see using another ASR in the
mean time, recording their calls and feeding the audio to Pocketsphinx for
training, then switching to Pocketspinx once it's "tuned up." At least this
way a business doesn't have to deal with a "virgin" pocketsphinx.
Mark
--
This message has been scanned for viruses and
dangerous content by MailScanner, and is
believed to be clean.
|
A Good Credit Score is 700 or Above. See yours in just 2 easy steps! |
|
Back to top |
|
|
brian at freeswitch.org Guest
|
Posted: Tue Jan 13, 2009 1:46 pm Post subject: [Freeswitch-users] FreeSWITCH, MRCP and Perl |
|
|
Well I also want to have someone take pocketsphinx and flite and build an opensource speech server and maybe gain some momentum to improve it. btw pocketsphinx supports jsgf, I need to update mod_pocketsphinx to do that but I want to work with DHD to figure out how to load the dictionary once... and just load grammar files moving forward.
/b
On Jan 13, 2009, at 12:31 PM, mszlazak@aol.com (mszlazak@aol.com) wrote:
Quote: | Hi Paul,
If you mean fixing up pocketsphinx (ps) for telephony instead of or in addition to working on unimrcp then this is the site of the person who created ps and he may have some advice.
http://www.cs.cmu.edu/~dhuggins/
Also, this was a post from the sphinx forums for adapting pocketsphinx for telephony.
http://sourceforge.net/forum/message.php?msg_id=5621913
I don't know how accurate it is but if accurate then here is that post to give you some of the issues involved:
-----------------
Well, there are issues in both the decoder and the interface with the
telephony application.
First about the decoder, pocketsphinx right now is the most supported
and most feature-reach decoder of the family, but in general it's still
oriented on the embedded devices. For telephony applications you
probably need to extend it a lot. The features that are currently
missing are probably:
* Out-of-box support for multiple recognizers (probably more a freeswitch
issue and a model training issue, for example we have no free
male/female model).
* Speaker clustering.
* Automatic VTLN estimation from pitch (This looks simple).
* Good endpointer.
* Discriminative training support in SphinxTrain (Huge task).
* Good and clean support for a garbage model to be able to filter out
out of grammar words.
* Embedded RASTA extraction and RASTA model training.
* Advanced features extraction
Another issue is dialog tracking and understanding. CMU folks are doing
work on dialog systems, for example Raven is available
http://www.ravenclaw-olympus.org/systems_overview.html
It would be worth to look on it and try to integrate it into
freepbx. Decoder will need to support combined language model. As well
as you'll need a component for postprocessing. The postprocessing includes
disfluency removal, text normalization, text boundary detection. Integration
with nltk probably useful for sense extraction.
If you need more details on any of the above, feel free to ask.
-------------------
-----Original Message-----
From: Paul Herring <paulh@instruments.com (paulh@instruments.com)>
To: freeswitch-users@lists.freeswitch.org (freeswitch-users@lists.freeswitch.org)
Sent: Tue, 13 Jan 2009 8:18 am
Subject: [Freeswitch-users] FreeSWITCH, MRCP and Perl
Quote: | What would it take to put a budget together to for this project?
Date: Tue, 13 Jan 2009 01:55:36 -0500
From: mszlazak@aol.com (mszlazak@aol.com)
Subject: Re: [Freeswitch-users] FreeSWITCH, MRCP and Perl
To: freeswitch-users@lists.freeswitch.org (freeswitch-users@lists.freeswitch.org)
Message-ID: <8CB436312A08329-80C-1B5D@MBLK-M24.sysops.aol.com (8CB436312A08329-80C-1B5D@MBLK-M24.sysops.aol.com)>
Content-Type: text/plain; charset="us-ascii"
"My god" I would LOVE it if this is really the case and would praise
pocketsphinx (PS) and FS to no end. But my experience has been different.
First, I tried the pizza demo with a soft phone and later by outside phone
calls to my Linksys 3102 pstn-to-voip gateway.
Second, I tried these two set-ups again but with Voxeo's Prophecy ASR.
Both are as is and by this I mean there was no training of PocketSphinx just
running the pizza demo and with Prophecy there is no training because it
can't be trained.
Prophecy is quite good but the FS/Pocketsphinx pizza demo isn't and I
couldn't use it at a pizza join. Also, I get a much better experience when
calling LumenVox and trying their pizza demo.
Now, maybe Prophecy is the type of asr that doesn't require hours of
training to make it speaker independent. I know that the Sphinx family are
the types of ASR that do need this.
So, if there is some settings for adaptation of Pocketsphinx for speaker
independence then are they turned on?
?
How many hours of calls to a business should an owner expect before
PocketSphinx gets good enough not to scare customers away?
If there are many hours needed then I could see using another ASR in the
mean time, recording their calls and feeding the audio to Pocketsphinx for
training, then switching to Pocketspinx once it's "tuned up." At least this
way a business doesn't have to deal with a "virgin" pocketsphinx.
Mark
--
This message has been scanned for viruses and
dangerous content by MailScanner, and is
believed to be clean.
|
A Good Credit Score is 700 or Above. See yours in just 2 easy steps!
_______________________________________________
Freeswitch-users mailing list
Freeswitch-users@lists.freeswitch.org (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
|
|
|
Back to top |
|
|
anthony.minessale at g... Guest
|
Posted: Tue Jan 13, 2009 2:08 pm Post subject: [Freeswitch-users] FreeSWITCH, MRCP and Perl |
|
|
We already have been collaborating with the maintainer of pocketsphinx for more than a year now, that's why we have a mod_pocketsphinx. His latest releases are based on our feedback so we are already doing that.
On Tue, Jan 13, 2009 at 12:31 PM, <mszlazak@aol.com (mszlazak@aol.com)> wrote:
Quote: | Hi Paul,
If you mean fixing up pocketsphinx (ps) for telephony instead of or in addition to working on unimrcp then this is the site of the person who created ps and he may have some advice.
http://www.cs.cmu.edu/~dhuggins/
Also, this was a post from the sphinx forums for adapting pocketsphinx for telephony.
http://sourceforge.net/forum/message.php?msg_id=5621913
I don't know how accurate it is but if accurate then here is that post to give you some of the issues involved:
-----------------
Well, there are issues in both the decoder and the interface with the
telephony application.
First about the decoder, pocketsphinx right now is the most supported
and most feature-reach decoder of the family, but in general it's still
oriented on the embedded devices. For telephony applications you
probably need to extend it a lot. The features that are currently
missing are probably:
* Out-of-box support for multiple recognizers (probably more a freeswitch
issue and a model training issue, for example we have no free
male/female model).
* Speaker clustering.
* Automatic VTLN estimation from pitch (This looks simple).
* Good endpointer.
* Discriminative training support in SphinxTrain (Huge task).
* Good and clean support for a garbage model to be able to filter out
out of grammar words.
* Embedded RASTA extraction and RASTA model training.
* Advanced features extraction
Another issue is dialog tracking and understanding. CMU folks are doing
work on dialog systems, for example Raven is available
http://www.ravenclaw-olympus.org/systems_overview.html
It would be worth to look on it and try to integrate it into
freepbx. Decoder will need to support combined language model. As well
as you'll need a component for postprocessing. The postprocessing includes
disfluency removal, text normalization, text boundary detection. Integration
with nltk probably useful for sense extraction.
If you need more details on any of the above, feel free to ask.
-------------------
-----Original Message-----
From: Paul Herring <paulh@instruments.com (paulh@instruments.com)>
To: freeswitch-users@lists.freeswitch.org (freeswitch-users@lists.freeswitch.org)
Sent: Tue, 13 Jan 2009 8:18 am
Subject: [Freeswitch-users] FreeSWITCH, MRCP and Perl
Quote: | What would it take to put a budget together to for this project?
Date: Tue, 13 Jan 2009 01:55:36 -0500
From: mszlazak@aol.com (mszlazak@aol.com)
Subject: Re: [Freeswitch-users] FreeSWITCH, MRCP and Perl
To: freeswitch-users@lists.freeswitch.org (freeswitch-users@lists.freeswitch.org)
Message-ID: <8CB436312A08329-80C-1B5D@MBLK-M24.sysops.aol.com (8CB436312A08329-80C-1B5D@MBLK-M24.sysops.aol.com)>
Content-Type: text/plain; charset="us-ascii"
"My god" I would LOVE it if this is really the case and would praise
pocketsphinx (PS) and FS to no end. But my experience has been different.
First, I tried the pizza demo with a soft phone and later by outside phone
calls to my Linksys 3102 pstn-to-voip gateway.
Second, I tried these two set-ups again but with Voxeo's Prophecy ASR.
Both are as is and by this I mean there was no training of PocketSphinx just
running the pizza demo and with Prophecy there is no training because it
can't be trained.
Prophecy is quite good but the FS/Pocketsphinx pizza demo isn't and I
couldn't use it at a pizza join. Also, I get a much better experience when
calling LumenVox and trying their pizza demo.
Now, maybe Prophecy is the type of asr that doesn't require hours of
training to make it speaker independent. I know that the Sphinx family are
the types of ASR that do need this.
So, if there is some settings for adaptation of Pocketsphinx for speaker
independence then are they turned on?
?
How many hours of calls to a business should an owner expect before
PocketSphinx gets good enough not to scare customers away?
If there are many hours needed then I could see using another ASR in the
mean time, recording their calls and feeding the audio to Pocketsphinx for
training, then switching to Pocketspinx once it's "tuned up." At least this
way a business doesn't have to deal with a "virgin" pocketsphinx.
Mark
--
This message has been scanned for viruses and
dangerous content by MailScanner, and is
believed to be clean.
|
A Good Credit Score is 700 or Above. See yours in just 2 easy steps!
_______________________________________________
Freeswitch-users mailing list
Freeswitch-users@lists.freeswitch.org (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
|
--
Anthony Minessale II
FreeSWITCH http://www.freeswitch.org/
ClueCon http://www.cluecon.com/
AIM: anthm
MSN:anthony_minessale@hotmail.com ([email]MSN%3Aanthony_minessale@hotmail.com[/email])
GTALK/JABBER/PAYPAL:anthony.minessale@gmail.com ([email]PAYPAL%3Aanthony.minessale@gmail.com[/email])
IRC: irc.freenode.net #freeswitch
FreeSWITCH Developer Conference
sip:888@conference.freeswitch.org ([email]sip%3A888@conference.freeswitch.org[/email])
iax:guest@conference.freeswitch.org/888
googletalk:conf+888@conference.freeswitch.org ([email]googletalk%3Aconf%2B888@conference.freeswitch.org[/email])
pstn:213-799-1400 |
|
Back to top |
|
|
|
|
|
You cannot post new topics in this forum You cannot reply to topics in this forum You cannot edit your posts in this forum You cannot delete your posts in this forum You cannot vote in polls in this forum
|
Powered by phpBB © 2001, 2005 phpBB Group
|