Edinburgh Research Explorer

Human-computer dialogue simulation using hidden Markov models

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

Original languageEnglish
Title of host publicationIEEE Workshop on Automatic Speech Recognition and Understanding, 2005.
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages290-295
ISBN (Electronic)0-7803-9479-8
ISBN (Print)0-7803-9478-X
DOIs
Publication statusPublished - 2005
EventIEEE Workshop on Automatic Speech Recognition and Understanding (ASRU'05) - Cancún, Mexico
Duration: 27 Nov 20051 Dec 2005

Workshop

WorkshopIEEE Workshop on Automatic Speech Recognition and Understanding (ASRU'05)
CountryMexico
CityCancún
Period27/11/051/12/05

Abstract

This paper presents a probabilistic method to simulate task-oriented human-computer dialogues at the intention level, that may be used to improve or to evaluate the performance of spoken dialogue systems. Our method uses a network of hidden Markov models (HMMs) to predict system and user intentions, where a "language model" predicts sequences of goals and the component HMMs predict sequences of intentions. We compare standard HMMs, input HMMs and input-output HMMs in an effort to better predict sequences of intentions. In addition, we propose a dialogue similarity measure to evaluate the realism of the simulated dialogues. We performed experiments using the DARPA communicator corpora and report results with three different metrics: dialogue length, dialogue similarity and precision-recall

Event

IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU'05)

27/11/051/12/05

Cancún, Mexico

Event: Workshop

ID: 27399219