tailieunhanh - Báo cáo khoa học: "Predicting User Reactions to System Error"

This paper focuses on the analysis and prediction of so-called aware sites, defined as turns where a user of a spoken dialogue system first becomes aware that the system has made a speech recognition error. We describe statistical comparisons of features of these aware sites in a train timetable spoken dialogue corpus, which reveal significant prosodic differences between such turns, compared with turns that ‘correct’ speech recognition errors as well as with ‘normal’ turns that are neither aware sites nor corrections. . | Predicting User Reactions to System Error Diane Litman and Julia Hirschberg AT T Labs-Research Florham Park NJ 07932 USA diane julia @ Marc Swerts IPO Eindhoven The Netherlands and CNTS Antwerp Belgium Abstract This paper focuses on the analysis and prediction of so-called aware sites defined as turns where a user of a spoken dialogue system first becomes aware that the system has made a speech recognition error. We describe statistical comparisons of features of these aware sites in a train timetable spoken dialogue corpus which reveal significant prosodic differences between such turns compared with turns that correct speech recognition errors as well as with normal turns that are neither aware sites nor corrections. We then present machine learning results in which we show how prosodic features in combination with other automatically available features can predict whether or not a user turn was a normal turn a correction and or an aware site. 1 Introduction This paper describes new results in our continuing investigation of prosodic information as a potential resource for error recovery in interactions between a user and a spoken dialogue system. In human-human interaction dialogue partners apply sophisticated strategies to detect and correct communication failures so that errors of recognition and understanding rarely lead to a complete breakdown of the interaction Clark and Wilkes-Gibbs 1986 . In particular various studies have shown that prosody is an important cue in avoiding such breakdown . Shimojima et al. 1999 . Human-machine interactions between a user and a spoken dialogue system SDS exhibit more frequent communication breakdowns due mainly to errors in the Automatic Speech Recognition ASR component of these systems. In such interactions however there is also evidence showing prosodic information may be used as a resource for error recovery. In previous work we identified new procedures to detect recognition .