Paper: Assessing and Improving the Performance of Speech Recognition for Incremental Systems

ACL ID N09-1043
Title Assessing and Improving the Performance of Speech Recognition for Incremental Systems
Venue Human Language Technologies
Session Main Conference
Year 2009
Authors

In incremental spoken dialogue systems, par- tial hypotheses about what was said are re- quired even while the utterance is still ongo- ing. We define measures for evaluating the quality of incremental ASR components with respect to the relative correctness of the par- tial hypotheses compared to hypotheses that can optimize over the complete input, the tim- ingof hypothesisformationrelativeto the por- tionoftheinputtheyareabout,andhypothesis stability, defined as the number of times they are revised. We show that simple incremen- tal post-processing can improve stability dra- matically, at the cost of timeliness (from 90% of edits of hypotheses being spurious down to 10% at a lag of 320ms). The measures are notindependent,and we showhowsystem de- signers can find a desired operating point...