KnowBrainer Speech Recognition
Decrease font size
Increase font size
Topic Title: AutoTranscribe Folder Agent and corrections to improve accuracy
Topic Summary: How to save voice files with text file using AutoTranscribe Folder Agent in Dragon Professional v10.1
Created On: 08/15/2009 09:31 PM
Status: Post and Reply
Linear : Threading : Single : Branch
Keyword
 08/15/2009 09:31 PM
User is offline View Users Profile Print this message


cberry22
Junior Member

Posts: 5
Joined: 08/15/2009

This is my first post to the forum, so I hope I explain my case well enough.  I had heard that in Dragon Professional v10.1, the AutoTranscribe Folder Agent was supposed to save the voice files with the text file so that you can come back later to do corrections.  Is this possible, or has Nuance not added this feature to Professional v10.1?

I am a medical transcriptionist trying to get set up to use Dragon to automatically transcribe digital dictation files received from several dictators.  I am not talking about echo-dictation, but using the dictated wav files of others and having Dragon auto-transcribe them, then I would then make corrections to help improve and increase the accuracy.

I just upgraded to Dragon Professional v10.1 and want to use the AutoTranscribe Folder Agent to batch transcribe dictations that I can come back to later to make corrections and help improve accuracy.  The only way I know of currently to do this is to choose Transcribe Recording into DragonPad and make corrections in the Spell box for each dictation.  Otherwise, the AutoTranscribe Folder Agent will only transcribe into a txt file, but not allow me to use Dragon to make corrections that will improve the accuracy.

Please, someone, if you have any idea how to accomplish this with Professional v10.1, please let me know.  I do not currently have the option of upgrading to Medical, so I am limited to what I can do with the Professional 10.1 version.  I hope this is enough information for you, but let me know if you need more info and what you need.

-----------------------
Dragon Professional 10.1 / KnowBrainer 2008
Core 2 Duo Extreme x6800 2.93 GHz / 3 GB RAM / SoundBlaster Audigy 2 ZS
Windows XP Pro SP3 / MS Office 2007



-------------------------

Dragon Professional 10.1 / KnowBrainer 2008 / Core 2 Duo Extreme x6800 2.93 GHz / 3 GB RAM / SoundBlaster Audigy 2 ZS / Windows XP Pro SP3 / MS Office 2007

 08/16/2009 06:19 AM
User is offline View Users Profile Print this message

Author Icon
R. Wilke
Top-Tier Member

Posts: 4391
Joined: 03/04/2007

Cberry,

basically what you want to do is feasable, but there are some caveats. Just two things, to start with.

1. For each speaker, an individual user profile must be created, for technical reasons.

2. For each speaker, an individual licence must be purchased, for legal reasons.

Other than that, there's nothing wrong with delegating editing/correcting dictation data, this method is also referred to as "deferred correction". If a person (a physician e.g.) has a valid licence of the Pro version, he can either dictate into his working station, or use a DVR in order to send his dictation to another workstation, and have them corrected by another person on a different workstation, where his copy of Dragon must be installed, and in this situation another licence wouldn't be necessary for the one who does the corrections, as long as he/she doesn't use the software "actively".

You can think of it in tems of licencing "per voice".

But, and if I understand you correctly here, it is not possible, technically, and not compliant with the EULA, for you to edit and/or correct someone else's dictation with just your own copy of Dragon.

Hope this helps, though.

Rüdiger

 



-------------------------

Well, it's past the point where we can make any changes in the code, but we can still make changes to the Easter Egg!

 08/16/2009 03:07 PM
User is offline View Users Profile Print this message


cberry22
Junior Member

Posts: 5
Joined: 08/15/2009

Rüdiger, thank you for replying to my post.  I understand about the individual user profiles for each voice - it just made sense to me that I would get better accuracy keeping them separate.

As regards the ability to do "deferred correction", great - that is what I want to do.  However, you didn't answer HOW to get Dragon to batch transcribe the dictations, saving (or synchronizing) the voice file with the txt file for later correction.  When I run the AutoTranscribe Folder Agent, it does NOT save the voice file with the txt file, so I cannot do the deferred correction.

Note:  I read the Help section for this and it said when adding a new task, "Select Task > New from the Synchronized Audio for Third Party Correction dialog box.  This displays the Synchronized Audio for Third Party Correction Task dialog box."  Nowhere do I see the words "Synchronized Audio for Third Party Correction Task" in the AutoTranscribe Folder Agent.  And when I click on Task / New, the dialog box says "Dragon NaturallySpeaking AutoTranscribe Folder Agent".  Again, I have Pro v10.1 installed so this should work, but it hasn't yet.

Regarding the Professional version being licensed for only one voice and only a secretary being allow to do deferred corrections (but not have their own user profile):  I guess I got some bad info in regards to what I needed to purchase for what I wanted it to do - or at least incomplete info about laws and licensing.  Even Nuance themselves did not tell me what you did when I spoke to them.

With regard to your comment about EULA law, I did some research and think I understand what you said.  Again, none of this was explained to me by anyone I spoke with and that is upsetting as I spoke with several "pros" and not one gave me the information you did (other than the new license for each voice when discussing the Preferred version I own).  Though I do not see what the difference is to the EULA if it is I who purchase a license for each voice and did the deferred corrections myself.  It is one license per voice purchased along with the dictator's permission to use VR for their dictations and to do deferred corrections.  I would think that complied with the EULA.  No one else is using it, just myself with the license for each dictator's voice.

Guess I'll have to figure out how to be more productive echo-dictating, though I'm doubtful it will work better than my current keyboard use (expansions, macros and templates, etc, are more productive for me than echo-dictating, at least currently).

Thank you, again, for taking the time to answer my post and to include the part about licensing and EULA.  I really didn't want to hear it, but am glad to learn about it now when I'm just getting started rather than later.


-------------------------

Dragon Professional 10.1 / KnowBrainer 2008 / Core 2 Duo Extreme x6800 2.93 GHz / 3 GB RAM / SoundBlaster Audigy 2 ZS / Windows XP Pro SP3 / MS Office 2007

 08/16/2009 04:21 PM
User is offline View Users Profile Print this message

Author Icon
Lunis Orcutt
Top-Tier Member

Posts: 22599
Joined: 10/01/2006

                                Welcome to the KnowBrainer Forums

We believe the only way that you can utilize differed correction, when transcribing recordings, is to transcribe a single recording only and then save that file with the dra option.


-------------------------


Click KB 2012 REV D to Download a 30 Day Evaluation of KnowBrainer 2012 


 


 


 

 08/16/2009 04:32 PM
User is offline View Users Profile Print this message


cberry22
Junior Member

Posts: 5
Joined: 08/15/2009

Lunis, I was afraid that was going to be the answer after failing to get the AutoTranscribe function to do it.  I have done it one at a time through Dragon's Transcribe Recording into DragonPad, but was hoping to be able to batch them through the AutoTranscribe function.  I was hoping I was just doing something wrong or missed something in the setup.

Thank you for taking the time to read and respond to my post.



-------------------------

Dragon Professional 10.1 / KnowBrainer 2008 / Core 2 Duo Extreme x6800 2.93 GHz / 3 GB RAM / SoundBlaster Audigy 2 ZS / Windows XP Pro SP3 / MS Office 2007

 08/19/2009 01:32 PM
User is offline View Users Profile Print this message


bk82
Top-Tier Member

Posts: 215
Joined: 08/04/2007

I could be wrong, but this feature is probably part of DNS Medical, as it says here on the Nuance website:

http://www.nuance.com/naturallyspeaking/products/whatsnew.asp (under Medical)

Improved Auto-Transcription
The Auto-Transcribe Folder Agent now creates a synchronized audio file along with the automatic transcript for deferred correction. Dragon Medical Enterprise 10 gives the Auto-Transcribe Agent the option of creating a synchronized audio (.DRA) file along with the transcript file, making it possible to later get the benefit of Playback and Correction.

If I understand this correctly, this feature is only part of Medical and you could obtain it by buying an upgrade.

Boris



-------------------------

DNS 12 Pro, Medical, Premium - German, English, French - Dragon Dictate 3.0, dns.comfort


 


Core i7 950, Windows 7 Ultimate 64-bit, Intel Core i7 950, 12 GB RAM, L2 2MB; Mic: Jabra Chromo NC 2400 USB.


 


www.in2comp.ch 

 08/19/2009 02:27 PM
User is offline View Users Profile Print this message

Author Icon
Lunis Orcutt
Top-Tier Member

Posts: 22599
Joined: 10/01/2006

The difference, as we understand it, is that a third-party can use their own user profile to make corrections on another person's dictation in Medical 10 and Legal 10 but not Pro 10. We may be wrong, as we haven't explored this feature but we don't think this would apply to the Auto Transcribe Agent.

-------------------------


Click KB 2012 REV D to Download a 30 Day Evaluation of KnowBrainer 2012 


 


 


 

 08/19/2009 03:19 PM
User is offline View Users Profile Print this message


cberry22
Junior Member

Posts: 5
Joined: 08/15/2009

bk82,

I think you are right in that it is not an option in the Professional version, although it shows as an option in the Help file.  In the Help for AutoTranscribe Folder Agent, under Creating a Task, it shows "Select Task > New from the Synchronized Audio for Third Party Correction dialog box. This displays the Synchronized Audio for Third Party Correction Task dialog box", and this is from my Pro version.  However, none of that is seen anywhere in my Pro version of the AutoTranscribe Folder Agent.  After talking with Tech Support, I was finally told that it is not an option in Professional.

So now I'm back to Transcribe Recording one at a time in DragonPad, which does allow you to save the dra file for later correction, which was not an option in the Preferred version I just upgraded from.

I want to thank everyone for helping me with my above questions.  Hopefully, I will eventually be able to upgrade to the Medical version, which should have pretty much everything I want/need - although it will probably take another generation or two before it will do the proofreading and corrections for me. ;-)

CBerry



-------------------------

Dragon Professional 10.1 / KnowBrainer 2008 / Core 2 Duo Extreme x6800 2.93 GHz / 3 GB RAM / SoundBlaster Audigy 2 ZS / Windows XP Pro SP3 / MS Office 2007

 08/19/2009 09:21 PM
User is offline View Users Profile Print this message

Author Icon
Lunis Orcutt
Top-Tier Member

Posts: 22599
Joined: 10/01/2006

This may or may not help but Nuance only has one NaturallySpeaking help file and manual and they use the same help file in all versions of NaturallySpeaking from Standard through Medical so not all referenced features are necessarily available.

-------------------------


Click KB 2012 REV D to Download a 30 Day Evaluation of KnowBrainer 2012 


 


 


 

 08/19/2009 09:42 PM
User is offline View Users Profile Print this message


cberry22
Junior Member

Posts: 5
Joined: 08/15/2009

Well now THAT's confusing!  At least the printer manufacturers who have several printer models sharing one book include which model certain features apply to.  If your going to include information completely irrelevant and even contradictory in a HELP file, then how much help is it?

But it does explain my confusion regarding what I read in the help file.  Thanks, Lunis, for passing this tidbit along.  And Nuance developers, if you ever read this post, PLEASE make the Help file more version-specific!

CBerry



-------------------------

Dragon Professional 10.1 / KnowBrainer 2008 / Core 2 Duo Extreme x6800 2.93 GHz / 3 GB RAM / SoundBlaster Audigy 2 ZS / Windows XP Pro SP3 / MS Office 2007

Statistics
27364 users are registered to the KnowBrainer Speech Recognition forum.
There are currently 1 users logged in.
The most users ever online was 2028 on 04/05/2013 at 07:36 PM.
There are currently 55 guests browsing this forum, which makes a total of 56 users using this forum.

FuseTalk Standard Edition v4.0 - © 1999-2013 FuseTalk™ Inc. All rights reserved.