The transcribed text has been analyzed by using part-of-speech tagging.
This process is a complex marking of parts of the speech both in terms of their definition (noun, verb, adjective etc.) and in relation to their context (the sentence or paragraph).
The part-of-speech analysis was performed by using a finite-state morphological transducer which was part of the Aperium Kyrgyz - Turkish translator. More information about the transducer can be found here:
http://www.lrec-conf.org/proceedings/lrec2012/summaries/1077.html