I already posted two days ago asking for help on building an article with CMU
to show the power of Conceptual Speech Recognition.
I want to make sure CMU Sphinx is the right engine for me. As such, I need the
following:
1) A Windows based SR engine.
2) It must be able to accept an ARPA compliant language model.
3) For each time-slice, it must be able to return the N-Best word latices with
corresponding scores.
If the SR engine does not do it out of the box, it must be possible to get it
to a point where it would get there (code changes).
Advise if I am considering the right SR engine or if I should look somewhere
else.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
I already posted two days ago asking for help on building an article with CMU
to show the power of Conceptual Speech Recognition.
I want to make sure CMU Sphinx is the right engine for me. As such, I need the
following:
1) A Windows based SR engine.
2) It must be able to accept an ARPA compliant language model.
3) For each time-slice, it must be able to return the N-Best word latices with
corresponding scores.
If the SR engine does not do it out of the box, it must be possible to get it
to a point where it would get there (code changes).
Advise if I am considering the right SR engine or if I should look somewhere
else.
Dear deltagreen, both CMUSphinx decoders are able to do what you need. I think
you need to proceed further.