Print Page | Close Window

Macros not found & gibberish transcriptions

Printed From: MSSpeech-Forum
Category: Windows™ Speech Recognition Forums
Forum Name: WSRToolkit
Forum Description: Questions and Answers for using the WSRToolkit features
URL: https://www.msspeech-forum.com/forum_posts.asp?TID=293
Printed Date: 10/Nov/2024 at 2:21am
Software Version: Web Wiz Forums 12.02 - http://www.webwizforums.com


Topic: Macros not found & gibberish transcriptions
Posted By: Esinem
Subject: Macros not found & gibberish transcriptions
Date Posted: 05/Jun/2012 at 5:35am
I downloaded the MS macros as instructed during installation but WSR says it can't find them. Do they need moving manually? If so, where?

Windows SR works well when I dictate but I ran transcription on my voice from a DVD tutorial (recorded under studio conditions) and the result was complete nonsense. I have run the training, even used the script from the DVD material I was working on and let WSR trawl through sample documents. The results are still totally unusable and reminiscent of SR in its infancy. Can I improve the success rate, apart from more SR training, or is that as good as it gets?  

I would be interested in feedback from other users of the transcription facility.



Replies:
Posted By: mmarkoe_admin
Date Posted: 05/Jun/2012 at 10:51am
Originally posted by Esinem Esinem wrote:

I downloaded the MS macros as instructed during installation but WSR says it can't find them. Do they need moving manually? If so, where?
WSRMacros.exe is located at:
C:\Program Files\WSRMacros
You said you downloaded WSRMacros. Did you install it from the download? Once installed and WSRMacros are started, you should see a blue oval icon in lower right of screen. RIGHT CLICK this and go to Security. Set Security Level to low and create Signing Certificate.

 
Quote Windows SR works well when I dictate but I ran transcription on my voice from a DVD tutorial (recorded under studio conditions) and the result was complete nonsense. I have run the training, even used the script from the DVD material I was working on and let WSR trawl through sample documents. The results are still totally unusable and reminiscent of SR in its infancy. Can I improve the success rate, apart from more SR training, or is that as good as it gets?
 
The page for the WSRToolkit says:
"Transcription reads .WAV files from a digital recorder and transcribes it to text. This is meant to be used by the person who has a personal user profile and dictates as they would in front of the computer using good enunciation and punctuation. It is not meant to transcribe multiple voices from a meeting."
 
There may be one or more reasons for the problem.
  • Are you inputting the .WAV directly into the computer instead of playing it through a microphone?
  • Is the .WAV file in the proper audio format (16 bit, 44100 Hz)
  • Is there one person speaking on the DVD or more than one?
  • Is the person speaking on the DVD dictation punctuation which helps with context decoding?

Marty Markoe, eMicrophones, Inc.

 




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