I wonder if I am using bad decoder parameters set.
Can somebody please confirm what parameters should be used with that hub4spanish acoustic model? I mean sampling freq rate, upperf/llowerf, feat-type, ... and other sphinx3_decode run-time parameters.
Thank you!
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
hi,
I am trying to use sphinx3 open source spanish acoustic model found in
http://www.speech.cs.cmu.edu/sphinx/models/hub4spanish_itesm/ but I am getting very poor results.
I wonder if I am using bad decoder parameters set.
Can somebody please confirm what parameters should be used with that hub4spanish acoustic model? I mean sampling freq rate, upperf/llowerf, feat-type, ... and other sphinx3_decode run-time parameters.
Thank you!