I am new into CMU Sphinx, use Microsoft Speech Platform to recognize voice, but this engine is not update since 2013 year.
So, can CMU Sphinx recognize live speech from audio stream?
Some cases:
Operator get call, User speak and pronounce word "bad service"-Sphinx catch this phraze.
Operator says:"Where" - and User says where he got bad service.
So, can Sphinx catch where it is?
As i understand , i shoud create grammar with keywords (bad service,good service and so on).
And create grammar with georgraphical places of offices.
So, can Sphinx work with this case?
Thank you!
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
I am new into CMU Sphinx, use Microsoft Speech Platform to recognize voice, but this engine is not update since 2013 year.
So, can CMU Sphinx recognize live speech from audio stream?
Some cases:
Operator get call, User speak and pronounce word "bad service"-Sphinx catch this phraze.
Operator says:"Where" - and User says where he got bad service.
So, can Sphinx catch where it is?
As i understand , i shoud create grammar with keywords (bad service,good service and so on).
And create grammar with georgraphical places of offices.
So, can Sphinx work with this case?
Thank you!
Yes
If you want details beyond simple keywords you need to run full scale transcription with domain-specific language model as described in our tutorial:
http://cmusphinx.sourceforge.net/wiki/tutoriallmadvanced
There should be no problem with it.