From hjsohn70 at hotmail.de  Wed Nov  3 02:19:10 2010
From: hjsohn70 at hotmail.de (HJin Sohn)
Date: Wed, 3 Nov 2010 07:19:10 +0100
Subject: [Olympus developers 260]:  installing problem
Message-ID: <SNT128-W261422AAB13262738B69B7B04A0@phx.gbl>


Hi, 
 
 I am a NLp developer in Korea and want to use OLYMPUS. 
I have installed all needed programms except a TTS system(MS , Fliter etc..)
 
When i try build Olympus, I have the following message:
 
/*................................................................................................
Can't locate Tools\logios\scripts\Logios.pm in @ INC(@INC contains
: Build C:Perl/site/lib/ C:/Perl/lib .0 at Build/OlympusBuild.pm line 85
........................................................................*/
 
 
Perl is installed in my PC under C:\Perl. 
Could you tell me how can I solve this problem?
 
Regards,
Andy Sohn
  		 	   		  
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.srv.cs.cmu.edu/pipermail/olympus-developers/attachments/20101103/63a72fc4/attachment.html

From mrmarge at cs.cmu.edu  Wed Nov  3 15:21:11 2010
From: mrmarge at cs.cmu.edu (Matthew Marge)
Date: Wed, 3 Nov 2010 15:21:11 -0400
Subject: [Olympus developers 261]: Re: installing problem
In-Reply-To: <SNT128-W261422AAB13262738B69B7B04A0@phx.gbl>
References: <SNT128-W261422AAB13262738B69B7B04A0@phx.gbl>
Message-ID: <AANLkTimOhu9AK6Zg0uKYrL3gE5UhYotPEaE1GNMyqG_g@mail.gmail.com>

Can you send the full build log?

On Wed, Nov 3, 2010 at 2:19 AM, HJin Sohn <hjsohn70 at hotmail.de> wrote:

>  Hi,
>
>  I am a NLp developer in Korea and want to use OLYMPUS.
> I have installed all needed programms except a TTS system(MS , Fliter
> etc..)
>
> When i try build Olympus, I have the following message:
>
>
> /*................................................................................................
> Can't locate Tools\logios\scripts\Logios.pm in @ INC(@INC contains
> : Build C:Perl/site/lib/ C:/Perl/lib .0 at Build/OlympusBuild.pm line 85
> ........................................................................*/
>
>
> Perl is installed in my PC under C:\Perl.
> Could you tell me how can I solve this problem?
>
> Regards,
> Andy Sohn
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.srv.cs.cmu.edu/pipermail/olympus-developers/attachments/20101103/27be99a3/attachment-0001.html

From mccallum at cs.toronto.edu  Wed Nov 17 13:49:53 2010
From: mccallum at cs.toronto.edu (Anthony McCallum)
Date: Wed, 17 Nov 2010 13:49:53 -0500
Subject: [Olympus developers 262]:  building olympus
Message-ID: <583CA29A-D400-4B26-BFBC-AD4C885FE66A@cs.toronto.edu>

Hi,
I hope this is the right place to ask this.  Will Visual Studio 2010  
suffice for building olympus?  I've installed it, but get this error  
when building olympus:


Running command: "C:\Program Files\CMake 2.8\bin\cmake.exe" -G "Visual  
Studio 9 2008" -D KALLIOPE_USE_FLITE:BOOL=yes -D  
KALLIOPE_USE_SAPI:BOOL=no ../..

CMake Error: CMake was unable to find a build program corresponding to  
"Visual Studio 9 2008".  CMAKE_MAKE_PROGRAM is not set.  You probably  
need to select a different build tool.

CMake Error: Could not find cmake module file:C:/Users/anthony/Desktop/ 
olympus/Build/cmake/CMakeFiles/CMakeCCompiler.cmake

CMake Error: Could not find cmake module file:C:/Users/anthony/Desktop/ 
olympus/Build/cmake/CMakeFiles/CMakeCXXCompiler.cmake

-- Configuring incomplete, errors occurred!

CMake did not generate a Visual Studio solution


I'm just wondering if there is a way around this, or if I need to  
install VS 2008 instead.

Thanks,
Anthony
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.srv.cs.cmu.edu/pipermail/olympus-developers/attachments/20101117/3a5bf529/attachment.html

From ssiiys at hotmail.com  Wed Nov 17 16:36:09 2010
From: ssiiys at hotmail.com (pablo san juan)
Date: Wed, 17 Nov 2010 21:36:09 +0000
Subject: [Olympus developers 263]:  Question
Message-ID: <SNT126-W46279F92B3504A7441CECBC5380@phx.gbl>


Please, what is appropriate to install the prerequisites: tested version or recommend version.

Thank you for your time.

Pablo


 		 	   		  
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.srv.cs.cmu.edu/pipermail/olympus-developers/attachments/20101117/fc2de666/attachment.html

From mrmarge at cs.cmu.edu  Wed Nov 17 21:13:18 2010
From: mrmarge at cs.cmu.edu (Matthew Marge)
Date: Wed, 17 Nov 2010 21:13:18 -0500
Subject: [Olympus developers 264]: Re: Question
In-Reply-To: <SNT126-W46279F92B3504A7441CECBC5380@phx.gbl>
References: <SNT126-W46279F92B3504A7441CECBC5380@phx.gbl>
Message-ID: <AANLkTi=+qMKfk3c1DRA_O+zaWR5ZFhFJf9ZadR78bGMO@mail.gmail.com>

Start with the tutorials:
http://wiki.speech.cs.cmu.edu/olympus/index.php/Tutorials_Overview

Can you please explain the difference between the two and the link you're
referring to?

On Wed, Nov 17, 2010 at 4:36 PM, pablo san juan <ssiiys at hotmail.com> wrote:

>  Please, what is appropriate to install the prerequisites: *tested **
> version* or* recommend version*.
>
> Thank you for your time.
>
> Pablo
>
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.srv.cs.cmu.edu/pipermail/olympus-developers/attachments/20101117/c40bd73f/attachment.html

From gparent+ at cs.cmu.edu  Thu Nov 18 16:05:11 2010
From: gparent+ at cs.cmu.edu (Gabriel Parent)
Date: Thu, 18 Nov 2010 16:05:11 -0500
Subject: [Olympus developers 265]:  speech level ("volume")
Message-ID: <4CE59507.2090601@cs.cmu.edu>

Hi,

I'm building a model to have my SDS adapt to the user.  I need the 
"volume" feature: for example, if a user starts speaking louder, there 
might be a bus passing by and thus we need to increase the volume of the 
synthesizer (it's a bad example, anyway you get the point).

Looking into the AudioServer, I found that the GMM VAD updates two 
variables : fNoiseLevel and fSpeechLevel.  I don't understand exactly 
how the GMM VAD works, but it seems it estimates the speech level using 
an histogram.  Would it be safe to use fSpeechLevel as my "volume" 
feature?  I tried going from whispering to shouting, and that value went 
from 9 to 17.  Just want to make sure I'm not making a dumb mistake.

Cheers,
Gabriel

From antoine.raux at gmail.com  Thu Nov 18 16:57:46 2010
From: antoine.raux at gmail.com (Antoine Raux)
Date: Thu, 18 Nov 2010 13:57:46 -0800
Subject: [Olympus developers 266]: Re: speech level ("volume")
In-Reply-To: <4CE59507.2090601@cs.cmu.edu>
References: <4CE59507.2090601@cs.cmu.edu>
Message-ID: <4CE5A15A.50504@gmail.com>

Yeah you got it right. The VAD assumes that the incoming audio is a 
mixture of background noise and speech so it looks for two peeks of the 
histogram, the lowest (quietest) one is noise, the highest is speech. So 
fSpeechLevel should be a good estimate of how loud the system hears the 
user (which is related to how loud they speak, how close they are to 
their phone, what phone they are using....).

antoine

On 11/18/2010 1:05 PM, Gabriel Parent wrote:
> Hi,
>
> I'm building a model to have my SDS adapt to the user.  I need the 
> "volume" feature: for example, if a user starts speaking louder, there 
> might be a bus passing by and thus we need to increase the volume of 
> the synthesizer (it's a bad example, anyway you get the point).
>
> Looking into the AudioServer, I found that the GMM VAD updates two 
> variables : fNoiseLevel and fSpeechLevel.  I don't understand exactly 
> how the GMM VAD works, but it seems it estimates the speech level 
> using an histogram.  Would it be safe to use fSpeechLevel as my 
> "volume" feature?  I tried going from whispering to shouting, and that 
> value went from 9 to 17.  Just want to make sure I'm not making a dumb 
> mistake.
>
> Cheers,
> Gabriel
>


From Alex.Rudnicky at cs.cmu.edu  Thu Nov 18 16:59:12 2010
From: Alex.Rudnicky at cs.cmu.edu (Alex Rudnicky)
Date: Thu, 18 Nov 2010 16:59:12 -0500
Subject: [Olympus developers 267]: Re: speech level ("volume")
In-Reply-To: <4CE59507.2090601@cs.cmu.edu>
References: <4CE59507.2090601@cs.cmu.edu>
Message-ID: <9C0D1A9F38D23E4290347EE31C22B0AF040C6FCE@e2k3.srv.cs.cmu.edu>

The VAD/endpointer considers the delta between the background noise and
the speech level; when it's big enough, speech is "detected". This
actually deals with the passing-bus problem, if the talker raises their
volume to compensate.

But there's any number of reasons why someone might speaker louder.

It might be better to key synthesis volume to fNoiseLevel, and try to
always keep it a certain value above the imputed background noise (say
15-20dN).

Alex


-----Original Message-----
From: olympus-developers-bounces at mailman.srv.cs.cmu.edu
[mailto:olympus-developers-bounces at mailman.srv.cs.cmu.edu] On Behalf Of
Gabriel Parent
Sent: Thursday, November 18, 2010 4:05 PM
To: olympus-developers at mailman.srv.cs.cmu.edu
Subject: [Olympus developers 265]: speech level ("volume")

Hi,

I'm building a model to have my SDS adapt to the user.  I need the 
"volume" feature: for example, if a user starts speaking louder, there 
might be a bus passing by and thus we need to increase the volume of the

synthesizer (it's a bad example, anyway you get the point).

Looking into the AudioServer, I found that the GMM VAD updates two 
variables : fNoiseLevel and fSpeechLevel.  I don't understand exactly 
how the GMM VAD works, but it seems it estimates the speech level using 
an histogram.  Would it be safe to use fSpeechLevel as my "volume" 
feature?  I tried going from whispering to shouting, and that value went

from 9 to 17.  Just want to make sure I'm not making a dumb mistake.

Cheers,
Gabriel


From antoine.raux at gmail.com  Thu Nov 18 16:56:27 2010
From: antoine.raux at gmail.com (Antoine Raux)
Date: Thu, 18 Nov 2010 13:56:27 -0800
Subject: [Olympus developers 268]: Re: speech level ("volume")
In-Reply-To: <4CE59507.2090601@cs.cmu.edu>
References: <4CE59507.2090601@cs.cmu.edu>
Message-ID: <4CE5A10B.5020905@gmail.com>

Yeah you got it right. The VAD assumes that the incoming audio is a 
mixture of background noise and speech so it looks for two peeks of the 
histogram, the lowest (quietest) one is noise, the highest is speech. So 
fSpeechLevel should be a good estimate of how loud the system hears the 
user (which is related to how loud they speak, how close they are to 
their phone, what phone they are using....).

antoine

On 11/18/2010 1:05 PM, Gabriel Parent wrote:
> Hi,
>
> I'm building a model to have my SDS adapt to the user.  I need the 
> "volume" feature: for example, if a user starts speaking louder, there 
> might be a bus passing by and thus we need to increase the volume of 
> the synthesizer (it's a bad example, anyway you get the point).
>
> Looking into the AudioServer, I found that the GMM VAD updates two 
> variables : fNoiseLevel and fSpeechLevel.  I don't understand exactly 
> how the GMM VAD works, but it seems it estimates the speech level 
> using an histogram.  Would it be safe to use fSpeechLevel as my 
> "volume" feature?  I tried going from whispering to shouting, and that 
> value went from 9 to 17.  Just want to make sure I'm not making a dumb 
> mistake.
>
> Cheers,
> Gabriel
>


From nkatsaounos at sch.gr  Tue Nov 23 07:53:33 2010
From: nkatsaounos at sch.gr (=?iso-8859-7?B?zd/q7/IgyuH08+Hv/e3v8g==?=)
Date: Tue, 23 Nov 2010 14:53:33 +0200
Subject: [Olympus developers 269]:  AudioServer creates 0-byte audio
Message-ID: <004b01cb8b0d$6fe5fbd0$4fb1f370$@gr>

Hi,

I am using Olympus framework for my application (input from microphone).

I have the following problem: from time to time my application "stops"
working . The reason is that Audioserver component creates somehow a
zero-byte utterance. After this, PocketSphinx produces the appropriate error


 

ERROR: "ngram_search.c", line 950: Couldn't find <s> in first frame

[STD at 11:23:56.847 (733830)] unable to get hypothesis

 

After this, my application does not react any more to any input utterances.

Can anyone help on this? Had anyone had similar problem in his application?

 

My regards

Nikos Katsaounos

 

 

-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.srv.cs.cmu.edu/pipermail/olympus-developers/attachments/20101123/45f052d4/attachment.html

From contact at clinicaltrialmagnifier.com  Thu Nov 25 12:21:53 2010
From: contact at clinicaltrialmagnifier.com (Clinical Trial Magnifier)
Date: Fri, 26 Nov 2010 01:21:53 +0800
Subject: [Olympus developers 270]:  Clinical Trial Magnifier - now 24,
	290 subscribers from 157 countries
Message-ID: <REASONABLES617307b97b35ed3047eeb44289e5fe2d93ab@reasonables6173>

  

Dear Colleague, 

You are invited to subscribe to a new free electronic monthly newsletter, the Clinical Trial Magnifier ( http://t.rs-tk.com/t.aspx/subid/22624477/camid/54634/www.clinicalresearchclinic.com ). 

Clinical Trial Magnifier - October 2010 

The October Magnifier issue covers an analyses of the WHO Trials Registry database. The database was downloaded on September 3, 2010 including a total of 118,331 trials. The vast majority (n=99,840, 84.4%) of the studies are clinical trials. About one-third of the trials registered are industry-sponsored and two-thirds are non-industry sponsored trials. 

Twenty percent of all non-industry sponsored trials originate from trial registries in Australia  New Zealand, UK and Japan. In contrast, multi-national industry-sponsored trials are predominantly (96%) registered in the US trial registry. 

The US trial registry is recommended as the registry of choice for searching for industry-sponsored trials. The US trial registry also offers the user a much more powerful search engine than the WHO Trials Registry. 

Clinical Trial Magnifier Conference - Investigator Incentives Participation in Sponsored Trials 

The second Clinical Trial Magnifier Conference will be held in Kota Kinabalu, Sabah, Malaysia, on November 24-26, 2010. The conference theme and focus is Clinical Investigator Incentives for Participation in Industry-Sponsored Clinical Trials - http://www.CTMconference.com ( http://t.rs-tk.com/t.aspx/subid/22624477/camid/54634/www.CTMConference.com ).  

Please feel free to share or disseminate the CTM Conference information with fellow colleagues, in your organizations newsletters or websites. 

Yours Sincerely,  Johan PE Karlberg, MD, PhD Clinical Trials Centre The University of Hong Kong 

P.S. If you have any kind of queries or messages please contact me directly using:  EditorialBoard at ClinicalTrialMagnifier.com (  ) 

This email is sent to olympus-developers at cs.cmu.edu. Delete my email from the Magnifier database. ( http://s.rs-tk.com/Unsubscribe.aspx?sub=22624477&user=4658&campid=54634&type=h )  
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.srv.cs.cmu.edu/pipermail/olympus-developers/attachments/20101124/fb5b9bb6/attachment.html

From nkatsaounos at sch.gr  Mon Nov 22 09:35:01 2010
From: nkatsaounos at sch.gr (=?iso-8859-7?B?zd/q7/IgyuH08+Hv/e3v8g==?=)
Date: Mon, 22 Nov 2010 14:35:01 -0000
Subject: [Olympus developers 300]:  AudioServer creates 0-byte audio
Message-ID: <000901cb8a51$51d838e0$f588aaa0$@gr>

Hi,

I am using Olympus framework for my application (input from microphone).

I have the following problem: from time to time my application "stops"
working . The reason is that Audioserver component creates somehow a
zero-byte utterance. After this, PocketSphinx produces the appropriate error


 

ERROR: "ngram_search.c", line 950: Couldn't find <s> in first frame

[STD at 11:23:56.847 (733830)] unable to get hypothesis

 

After this, my application does not react any more to any input utterances.

Please find attached the corresponding log files.

Can anyone help on this? Had anyone had similar problem in his application?

 

My regards

Nikos Katsaounos

 

 

 

 

-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.srv.cs.cmu.edu/pipermail/olympus-developers/attachments/20101122/d5fd0cce/attachment-0001.html
-------------- next part --------------
A non-text attachment was scrubbed...
Name: MyGame-20101122-001-sphinx_desktop.log
Type: application/octet-stream
Size: 1424965 bytes
Desc: not available
Url : http://mailman.srv.cs.cmu.edu/pipermail/olympus-developers/attachments/20101122/d5fd0cce/MyGame-20101122-001-sphinx_desktop-0001.obj