A Maximum Latency Classifier for Listener Responses
2010 (English)In: Proceedings of SLTC 2010, Linköping, Sweden, 2010Conference paper (Refereed)
When Listener Responses such as “yeah”, “right” or “mhm” are uttered in a face-to-face conversation, it is not uncommon for the interlocutor to continue to speak in overlap, i.e. before the Listener becomes silent. We propose a classifier which can classify incoming speech as a Listener Response or not before the talk-spurt ends. The classifier is implemented as an upgrade of the Embodied Conversational Agent developed in the SEMAINE project during the eNTERFACE 2010 workshop.
Place, publisher, year, edition, pages
Linköping, Sweden, 2010.
Computer Science Language Technology (Computational Linguistics)
IdentifiersURN: urn:nbn:se:kth:diva-52165OAI: oai:DiVA.org:kth-52165DiVA: diva2:465460
SLTC 2010, The Third Swedish Language Technology Conference (SLTC 2010), Linköping, October 27-29, 2010
tmh_import_11_12_14 QC 201112192011-12-142011-12-142011-12-19Bibliographically approved