Integrating incremental speech recognition and POMDP-based dialogue systems

Ethan O. Selfridge, Iker Arizmendi, Peter Heeman, Jason D. Williams

Research output: Chapter in Book/Report/Conference proceedingConference contribution

16 Scopus citations

Abstract

The goal of this paper is to present a firststep toward integrating Incremental SpeechRecognition (ISR) and Partially-ObservableMarkov Decision Process (POMDP) based dialoguesystems. The former provides supportfor advanced turn-taking behavior whilethe other increases the semantic accuracy ofspeech recognition results. We present an IncrementalInteraction Manager that supportsthe use of ISR with strictly turn-based dialoguemanagers. We then show that usinga POMDP-based dialogue manager with ISRsubstantially improves the semantic accuracyof the incremental results.

Original languageEnglish (US)
Title of host publicationSIGDIAL 2012 - 13th Annual Meeting of the Special Interest Group on Discourse and Dialogue, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages275-279
Number of pages5
ISBN (Electronic)9781937284442
StatePublished - 2012
Event13th Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGDIAL 2012 - Seoul, Korea, Republic of
Duration: Jul 5 2012Jul 6 2012

Other

Other13th Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGDIAL 2012
CountryKorea, Republic of
CitySeoul
Period7/5/127/6/12

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Modeling and Simulation
  • Human-Computer Interaction

Fingerprint Dive into the research topics of 'Integrating incremental speech recognition and POMDP-based dialogue systems'. Together they form a unique fingerprint.

Cite this