Change search
ReferencesLink to record
Permanent link

Direct link
Context cues for classification of competitive and collaborative overlaps
KTH, School of Computer Science and Communication (CSC), Speech, Music and Hearing, TMH, Speech Communication and Technology.
Show others and affiliations
2012 (English)In: Speech Prosody 2012, Shanghai, China, 2012, 721-724 p.Conference paper (Refereed)
Abstract [en]

Being able to respond appropriately to users’ overlaps should be seen as one of the core competencies of incremental dialogue systems. At the same time identifying whether an interlocutor wants to support or grab the turn is a task which comes natu- rally to humans, but has not yet been implemented in such sys- tems. Motivated by this we first investigate whether prosodic characteristics of speech in the vicinity of overlaps are signifi- cantly different from prosodic characteristics in the vicinity of non-overlapping speech. We then test the suitability of differ- ent context sizes, both preceding and following but excluding features of the overlap, for the automatic classification of col- laborative and competitive overlaps. We also test whether the fusion of preceding and succeeding contexts improves the clas- sification. Preliminary results indicate that the optimal context for classification of overlap lies at 0.2 seconds preceding the overlap and up to 0.3 seconds following it. We demonstrate that we are able to classify collaborative and competitive overlap with a median accuracy of 63%.

Place, publisher, year, edition, pages
Shanghai, China, 2012. 721-724 p.
National Category
Computer Science Language Technology (Computational Linguistics)
URN: urn:nbn:se:kth:diva-109391ScopusID: 2-s2.0-84902962248OAI: diva2:581719
Speech Prosody 2012

tmh_import_13_01_02, tmh_id_3791. QC 20130114

Available from: 2013-01-02 Created: 2013-01-02 Last updated: 2013-01-14Bibliographically approved

Open Access in DiVA

No full text


Search in DiVA

By author/editor
Oertel, Catharine
By organisation
Speech Communication and Technology
Computer ScienceLanguage Technology (Computational Linguistics)

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 13 hits
ReferencesLink to record
Permanent link

Direct link