A Conditional Model For Triggering Understanding Actions In A Speech Understanding System

A conditional model is introduced for triggering understanding actions that correct errors of frame hypothesization and composition. Experimental evidence is provided using the French MEDIA corpus that these models trained with automatic speech recognition hypotheses trigger effective corrections of more than half of the errors. The overall frame recall increases from 0.76 to 0.84 while precision increases from 0.78 to 0.85. The number of fully corrected dialog turns increases of 8.8% making about half of the turns fully correct.