The following forum message was posted by shantrip at
http://sourceforge.net/projects/marf/forums/forum/213052/topic/3782565:
Hi Serguei..
I am planning to develop a pronunciation detection software where a given
word will be spoken by the user and saved as wav file.This file will be
compared with a predefined sound file and percentage of match calculated.The
program will check for only phonetic match so voice of different people wilh
same pronunciation should match.
I checked your Speaker Identification Application and that was really
great! ! But requirement of pronunciation is it should be speaker independant.
I checked out some other packages like cmu-sphinx4 ,but that was giving
good result at word match and results for phones were not very promising .Also
MFCC-DTW pair was giving some problem in interoperability for me. MARF for me
seems the best bet ,being a complete audio package .So, i would be grateful if
you can tell if such application is feasible using MARF?? Also, if yes
...please point me some direction of approach...
Thanks in advance!!
ShanTrip
PS:Sorry for long post ,had to make my situation clear.
------------------------------------------------------------------------------
The Palm PDK Hot Apps Program offers developers who use the
Plug-In Development Kit to bring their C/C++ apps to Palm for a share
of $1 Million in cash or HP Products. Visit us here for more details:
http://ad.doubleclick.net/clk;226879339;13503038;l?
http://clk.atdmt.com/CRS/go/247765532/direct/01/
_______________________________________________
marf-devel mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/marf-devel
