Print Page | Close Window

"Add from File" for all files in directory trees

Printed From: MSSpeech-Forum
Category: Windows™ Speech Recognition Forums
Forum Name: New Users & General Questions
Forum Description: Ask questions, give and get answers.
URL: https://www.msspeech-forum.com/forum_posts.asp?TID=15
Printed Date: 13/Nov/2024 at 10:49pm
Software Version: Web Wiz Forums 12.02 - http://www.webwizforums.com


Topic: "Add from File" for all files in directory trees
Posted By: rcoifman
Subject: "Add from File" for all files in directory trees
Date Posted: 10/Aug/2008 at 3:59pm

8/10/08: Forum posting: As a physician with thousands of reports in Microsoft Word format transcribed from dictation by a human typist and stored in a single directory tree I’d like to know if he WSR toolkit could be empowered to perform its "Add from File" function with all Word or TXT documents in a designated directory and subdirectories, without need to individually selecct each file?

If you add too many files is it possible to negatively impact speech recognition accuracy by somehow overloading the system?




Replies:
Posted By: Guests
Date Posted: 11/Aug/2008 at 11:30am
Hello rcoifman,

First, let me say 'Thank you' for using our WSR Toolkit.  I hope it is proving to be a useful tool for your speech recognition productivity.

Regarding your question about empowering the Toolkit to add entire folders of documents, we discussed this during the initial design/testing phase and decided not to include this in version 1.

I have been discussing this concept with my wife (a medical transcriptionist) and she believes that most physician's dictating styles can be represented by a half-dozen or so different document types.  In other words, each physician she types for has a particular style that can be summarized with only a few documents.  Do you find this to be the case for your dictation style?  If so, it will narrow down your "Add From File" requirements considerably.

It is possible that too many "Add From File" files might negatively impact recognition accuracy.  It may be prudent to add just a few and judge accuracy before adding more.  I don't believe it would "overload" the system, but may not have the desired effect of increased accuracy.

Note: You may also want to also consider the "Add To Dictionary" Toolkit option, different in concept than the "Add From File", to improve your dictation accuracy.

Hope you find this helpful.

BradT

PS - Are you using macros for your day-to-day work?  We (over in the macro forum) would love to hear of any macro needs (or wishes) you may have.


Posted By: cmwilkerson
Date Posted: 08/Oct/2008 at 10:01am
>>Note: You may also want to also consider the "Add To Dictionary" Toolkit option, different in concept than the "Add From File", to improve your dictation accuracy.<<
 
This specific tool, which in turn calls up another screen in MS Speech, needs to opened with a macro instead of multiple mouse clicks.  When a medical word is not recognized, a "Very fast," method is needed to add individual words.


-------------
Dr. Chris Wilkerson
Carson Doctors Group
MVP TabletPC
www.MedicalTabletPC.com
www.Digital-Doc.com



Posted By: mmarkoe
Date Posted: 08/Oct/2008 at 11:16am
Originally posted by cmwilkerson cmwilkerson wrote:

This specific tool, which in turn calls up another screen in MS Speech, needs to opened with a macro instead of multiple mouse clicks.  When a medical word is not recognized, a "Very fast," method is needed to add individual words.
This is actually already built into the Windows Speech Recognition system. Just say, "Open speech dictionary." Next say, "Add a new word." You can do this all by voice. Brad, the programming genius behind WSRToolkit, is on vacation this week, but I'll ask him to stop by and let you know if Add Words can be opened via a macro.
 
Please keep posting questions like these. The answers are not always obvious. There will be many new resources in the days, weeks and months to come for Windows Speech Recognition. For example:
1. Brad Trott's new book on macros is in the final editing stage and will hopefully be available within one week.
2. Dan Newman's video tutorial should be available also in one week or less.
3. Getting Started with Windows Speech Recognition, a short document describing how to get up to speed quickly should be available in 1-2 weeks.
4. Joe Buckle's s Trigram medical speech dictionary topics should be available anywhere from 1-3 months.

Numbers one and two above are going to sell for the outrageous cost of $9.99. Number three is going to be for free. At this time we have no idea what the cost of each topic in number four will be.
 
All of the above will be available through:
http://www.mymsspeech.com/ - http://www.mymsspeech.com


-------------
Marty Markoe, MVP
Microsoft Valued Partner
See us at: http://www.mymsspeech.com


Posted By: BradT
Date Posted: 08/Oct/2008 at 5:08pm
Originally posted by cmwilkerson cmwilkerson wrote:

... When a medical word is not recognized, a "Very fast," method is needed to add individual words.


Let's brainstorm a bit and figure out the most efficient way to accomplish this...

I have a speech macro in which you highlight the word (or phrase) then say "add to speech dictionary", or simply "add to dictionary" and it's done without any further promptings.

Maybe there's a quicker way?

Brad

PS - I'll work on getting some of the "goodies" re-posted to the forum download area.  I was having problems with my userid and it was deleted/re-created in an attempt to resolve the issue but apparently all my downloads are now gone. Cry





Print Page | Close Window

Forum Software by Web Wiz Forums® version 12.02 - http://www.webwizforums.com
Copyright ©2001-2019 Web Wiz Ltd. - https://www.webwiz.net