Here the Ascr (Unnorm) is calculated for each set of frames. I want to know
how to calculate this score. Please provide me some tutorial to learn it if
needed. Once thanks again for your concern
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
how to calculate acoustic score
Sorry, your question is not clear enough to have an answer.
What exactly is the issue you have? Do you want to access an acoustic score in
your application or what? Have you setup the recognizer already?
The more details you provide the faster you get the answer.
thanks for your reply friend.
I have a recogniser already which is built for Indian Languages.
When I decode a wav using sphinx3_decode I get a log file which shows acoustic
score(Unnormalised)
For example my log file is:-
Backtrace(002Copra)
FV:002Copra> WORD SFrm EFrm AScr(UnNorm) LMScore AScr+LScr AScale
fv:002Copra> <ln> 0 33 2172069 -105139 2066930 2295413
fv:002Copra> Copra 34 90 -1066428 -217810 -1284238 -267335
fv:002Copra> Banana_Red_Banana(3) 91 147 410995 -285501 125494 1083580
fv:002Copra> <ln> 148 500 18720473 -105139 18615334 20504022
FV:002Copra> TOTAL 20237109 -713589 </ln></ln>
Here the Ascr (Unnorm) is calculated for each set of frames. I want to know
how to calculate this score. Please provide me some tutorial to learn it if
needed. Once thanks again for your concern
Sure friend
Read this book
http://www.amazon.com/Spoken-Language-Processing-Algorithm-
Development/dp/0130226165
It describes everything