I"m currently trying integrate sphinx3 into a program that I'm writting that
will decode and transcribe radio traffic on fire/ems radio transmissions, I've
gotten sphinx3 onto the system but am struggeling with accuracy, is there any
way to increase accuracy (different language models etc) without having to
train each dispatcher on the system (I'd like to avoid that if at all
possible).
Thanks any ideas would be greatly appreciated.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
I"m currently trying integrate sphinx3 into a program that I'm writting that
will decode and transcribe radio traffic on fire/ems radio transmissions, I've
gotten sphinx3 onto the system but am struggeling with accuracy, is there any
way to increase accuracy (different language models etc) without having to
train each dispatcher on the system (I'd like to avoid that if at all
possible).
Thanks any ideas would be greatly appreciated.
From http://cmusphinx.sourceforge.net/wordpress/versions/
This decoder is
only intended for researchers who want to evaluate bleeding edge
methods in ASR like tree search method.
http://nshmyrev.blogspot.com/2009/08/how-to-improve-
accuracy.html