Statistical Methods for Spoken Dialogue Management

Nonfiction, Science & Nature, Mathematics, Statistics, Technology, Electronics
Cover of the book Statistical Methods for Spoken Dialogue Management by Blaise Thomson, Springer London
View on Amazon View on AbeBooks View on Kobo View on B.Depository View on eBay View on Walmart
Author: Blaise Thomson ISBN: 9781447149231
Publisher: Springer London Publication: January 8, 2013
Imprint: Springer Language: English
Author: Blaise Thomson
ISBN: 9781447149231
Publisher: Springer London
Publication: January 8, 2013
Imprint: Springer
Language: English

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.

View on Amazon View on AbeBooks View on Kobo View on B.Depository View on eBay View on Walmart

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.

More books from Springer London

Cover of the book Minimally Invasive Surgery for Achilles Tendon Disorders in Clinical Practice by Blaise Thomson
Cover of the book Congenital Displacement of the Hip Joint by Blaise Thomson
Cover of the book Syndrome-based Approach to Diagnosis by Blaise Thomson
Cover of the book Difficult Decisions in Thoracic Surgery by Blaise Thomson
Cover of the book Proceedings of the International Conference on Information Engineering and Applications (IEA) 2012 by Blaise Thomson
Cover of the book Recent Advances in the 3D Physiological Human by Blaise Thomson
Cover of the book Dynamic Surface Control of Uncertain Nonlinear Systems by Blaise Thomson
Cover of the book Design of Advanced Photocatalytic Materials for Energy and Environmental Applications by Blaise Thomson
Cover of the book Bone Implant Grafting by Blaise Thomson
Cover of the book Conflict and Catastrophe Medicine by Blaise Thomson
Cover of the book Stability and Stabilization of Linear Systems with Saturating Actuators by Blaise Thomson
Cover of the book Surgical Management of Benign Esophageal Disorders by Blaise Thomson
Cover of the book Computational Intelligence by Blaise Thomson
Cover of the book Potential Theory by Blaise Thomson
Cover of the book Breast Cancer by Blaise Thomson
We use our own "cookies" and third party cookies to improve services and to see statistical information. By using this website, you agree to our Privacy Policy