Detecting Uncertainty in Spoken Dialogues: An explorative research for the automatic detection of speaker uncertainty by using prosodic markers

Dral, Jeroen and Heylen, Dirk and Akker op den, Rieks (2011) Detecting Uncertainty in Spoken Dialogues: An explorative research for the automatic detection of speaker uncertainty by using prosodic markers. In: Affective Computing and Sentiment Analysis. Text, Speech, and Language Analysis, 45 . Springer Verlag, London, pp. 67-77. ISBN 9789400717565

PDF
Restricted to UT campus only
159Kb

Abstract:	This paper reports results in automatic detection of speaker uncertainty in spoken dialogues by using prosodic markers. For this purpose a substantial part of the AMI corpus (a multi-modal multi-party meeting corpus) has been selected and converted to a suitable format so its data could be analyzed for a selected set of prosodic features. In the absence of relevant stance annotations on (un)certainty, lexical markers (hedges) have been used to mark utterances as (un)certain. Results show that prosodic features can indeed be used to detect speaker uncertainty in spoken dialogues. The classifiers can tell uncertain from neutral utterances with an accuracy of 75% which is 25% over the baseline.
Item Type:	Book Section
Copyright:	© 2011 Springer
Faculty:	Electrical Engineering, Mathematics and Computer Science (EEMCS)
Research Group:	Human Media Interaction (HMI)
Link to this item:	http://purl.utwente.nl/publications/79612
Official URL:	http://dx.doi.org/10.1007/978-94-007-1757-2_6
Export this item as:	BibTeX EndNote HTML Citation Reference Manager

Show download statistics for this publication

Repository Staff Only: item control page