Statistical Methods for Spoken Dialogue Management

  • Blaise┬áThomson

Part of the Springer Theses book series (Springer Theses)

Table of contents

  1. Front Matter
    Pages i-xvii
  2. Blaise Thomson
    Pages 1-5
  3. Blaise Thomson
    Pages 7-25
  4. Blaise Thomson
    Pages 27-43
  5. Blaise Thomson
    Pages 45-55
  6. Blaise Thomson
    Pages 57-70
  7. Blaise Thomson
    Pages 71-81
  8. Blaise Thomson
    Pages 83-102
  9. Blaise Thomson
    Pages 103-104
  10. Back Matter
    Pages 105-136

About this book

Introduction

Speech is the most natural mode of communication and yet attempts to build systems which support robust habitable conversations between a human and a machine have so far had only limited success. A key reason is that current systems treat speech input as equivalent to a keyboard or mouse, and behaviour is controlled by predefined scripts that try to anticipate what the user will say and act accordingly. But speech recognisers make many errors and humans are not predictable; the result is systems which are difficult to design and fragile in use.

Statistical methods for spoken dialogue management takes a radically different view. It treats dialogue as the problem of inferring a user's intentions based on what is said. The dialogue is modelled as a probabilistic network and the input speech acts are observations that provide evidence for performing Bayesian inference. The result is a system which is much more robust to speech recognition errors and for which a dialogue strategy can be learned automatically using reinforcement learning. The thesis describes both the architecture, the algorithms needed for fast real-time inference over very large networks, model parameter estimation and policy optimisation.

This ground-breaking work will be of interest both to practitioners in spoken dialogue systems and to cognitive scientists interested in models of human behaviour.

Keywords

Bayesian Inference Probabilistic Network Speech Recognition Errors Speech Technology Spoken Dialogue Management

Authors and affiliations

  • Blaise┬áThomson
    • 1
  1. 1., Department of EngineeringUniversity of CambridgeCambridgeUnited Kingdom

Bibliographic information

  • DOI https://doi.org/10.1007/978-1-4471-4923-1
  • Copyright Information Springer-Verlag London 2013
  • Publisher Name Springer, London
  • eBook Packages Engineering
  • Print ISBN 978-1-4471-4922-4
  • Online ISBN 978-1-4471-4923-1
  • Series Print ISSN 2190-5053
  • Series Online ISSN 2190-5061
  • About this book