Human-computer dialogue simulation using hidden Markov models

Heriberto Cuayáhuitl, S. Renals, O. Lemon, H. Shimodaira

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

Abstract / Description of output

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


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


Dive into the research topics of 'Human-computer dialogue simulation using hidden Markov models'. Together they form a unique fingerprint.

Cite this