Helping agents help their users despite imperfect speech recognition

Joshua B. Gordon, Rebecca Jane Passonneau, Susan L. Epstein

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

5 Scopus citations

Abstract

Spoken language is an important and natural way for people to communicate with computers. Nonetheless, habitable, reliable, and efficient human-machine dialogue remains difficult to achieve. This paper describes a multi-threaded semisynchronous architecture for spoken dialogue systems. The focus here is on its utterance interpretation module. Unlike most architectures for spoken dialogue systems, this new one is designed to be robust to noisy speech recognition through earlier reliance on context, a mixture of rationales for interpretation, and fine-grained use of confidence measures. We report here on a pilot study that demonstrates its robust understanding of users' objectives, and we compare it with our earlier spoken dialogue system implemented in a traditional pipeline architecture. Substantial improvements appear at all tested levels of recognizer performance.

Original languageEnglish (US)
Title of host publicationHelp Me Help You
Subtitle of host publicationBridging the Gaps in Human-Agent Collaboration - Papers from the AAAI Spring Symposium, Technical Report
Pages12-17
Number of pages6
StatePublished - Aug 15 2011
Event2011 AAAI Spring Symposium - Stanford, CA, United States
Duration: Mar 21 2011Mar 23 2011

Publication series

NameAAAI Spring Symposium - Technical Report
VolumeSS-11-05

Other

Other2011 AAAI Spring Symposium
CountryUnited States
CityStanford, CA
Period3/21/113/23/11

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Helping agents help their users despite imperfect speech recognition'. Together they form a unique fingerprint.

Cite this