Home » forums » Dragon » NaturallySpeaking

How do document contexts improve accuracy?

Submitted by ara_vartanian on Mon, 05/08/2006 - 23:40.

I was wondering if anyone knew something about the inner workings of how Dragon weights recent utterances. It seems to me that if I use an obscure word and Dragon gets it right or if I correct it that Dragon is much more likely to recognize it in the next sentence. Does Dragon pay attention to contexts in this way?

The reason I ask is this: I am experimenting with a program that exclusively uses the command mode. I have noticed in the command mode that my accuracy is far worse than in dictation mode. I was wondering if perhaps a lack of context explains this.

And then I was wondering if there was anything I could do about it. For example, was there any way of "simulating" the context so that Dragon can have that memory of recent utterances?

Thanks in advance for any help or insight.

‹ Dragon 9 Preferred and Firefox Cure for a hypersensitive microphone ›
»

Comment viewing options

Select your preferred way to display the comments and click "Save settings" to activate your changes.

There have been quite a few

Submitted by Matt Chambers on Tue, 05/09/2006 - 19:40.

There have been quite a few discussions about the importance of context for speech recognition on this forum. If you do some searches, I think you'll find some good posts, including this thread:

http://www.speechcomputing.com/node/717

»

Comment viewing options

Select your preferred way to display the comments and click "Save settings" to activate your changes.




view recent posts