KnowBrainer Speech Recognition
Decrease font size
Increase font size
Topic Title: why dragon is great
Topic Summary: auto transcribe folder
Created On: 04/22/2022 01:10 PM
Status: Post and Reply
Linear : Threading : Single : Branch
 why dragon is great   - matthewls - 04/22/2022 01:10 PM  
 why dragon is great   - dilligence - 04/24/2022 03:27 PM  
 why dragon is great   - Lunis Orcutt - 04/24/2022 07:45 PM  
Keyword
 04/22/2022 01:10 PM
User is offline View Users Profile Print this message

Author Icon
matthewls
Top-Tier Member

Posts: 755
Joined: 10/01/2006

I guess that for most people simple speech-to-text functionality is all they need--or think they want. But after decades of DNS use, building macro libraries etc., I just today discovered another great feature that I wouldn't ever want to lose: the auto transcribe folder. I had to write a powerpoint lecture for net viewing, complete with audio and video. The ppt features were insufficient, so I recorded my lecture in snippets using some Linux utility I found and added them to the ppt slide show. I don't remember what I said, and listening to the show would be painful. Voila, the ATF. All lecture snippets in text. Yippee!

 04/24/2022 03:27 PM
User is offline View Users Profile Print this message

Author Icon
dilligence
Top-Tier Member

Posts: 1526
Joined: 08/16/2010

For those who want to create a voice command to launch the agent in DPI 15:

 

AppBringUp "C:\Program Files (x86)\Nuance\NaturallySpeaking15\Program\tagent.exe"

 

Auto Transcribe Folder Agent indeed can be useful. Transcribing more or less "naturally spoken" audio may result in a better recognition rate compared to direct dictation in a window, where one might be tempted to use shorter sentences (I do :-().

 

But, I hope the next DPI version supports higher bitrates. Currently only WAV 16-bit 44100 will work (with a maximum around 1536kbps). The same appears to be true with MP3, no 48 kHz support. At least on my system...

 

I do a lot of screen recordings with audio and transcribing sections would be useful, but my screen recorder (Bandicam) won't allow me to record lower than 24-bit Waves. In order to transcribe I first need to convert to Signed 16-bit with Audacity which is cumbersome...



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

https://speechproductivity.eu


Turbocharge your Dragon® productivity with 40 Power Addons

 04/24/2022 07:45 PM
User is offline View Users Profile Print this message

Author Icon
Lunis Orcutt
Top-Tier Member

Posts: 39832
Joined: 10/01/2006

The average man’s speaking voice typically has a fundamental frequency range between 85 Hz and 155 Hz. A woman’s speech range is about 165 Hz to 255 Hz. Note that overtones can range as high as 6000 or 7000 Hz but 48 bit sampling won't make any difference because Dragon filters out higher frequencies. DragonSystems (original manufacturer) deliberately set Dragon's frequency response lower so that substandard microphones could reproduce acceptology accuracy. Nuance doubled Dragons frequency response in Ver. 11 because it was dropping some of the higher overtones. Simply put, increasing Dragons frequency response will not help and is unlikely to change. 



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

Change "No" to "Know" w/KnowBrainer 2020
Trial Downloads
Dragon/Sales@KnowBrainer.com 
(615) 884-4558 ex 1

KnowBrainer Speech Recognition » KnowBrainer Software and Support » why dragon is great

Statistics
32306 users are registered to the KnowBrainer Speech Recognition forum.
There are currently 1 users logged in.
The most users ever online was 12124 on 09/09/2020 at 04:59 AM.
There are currently 404 guests browsing this forum, which makes a total of 405 users using this forum.

FuseTalk Standard Edition v4.0 - © 1999-2022 FuseTalk™ Inc. All rights reserved.