THE STATISTICAL APPROACH TO THE DESIGN OF SPOKEN DIALOGUE SYSTEMS
S.J. Young
September 2002
Statistical methods have long been the dominant approach in speech recognition and probabilistic modelling in ASR is now a mature technology. The use of statistical methods in other areas of spoken dialogue is however more recent and much less mature. The aim of this report is to review the whole spoken dialogue system from a statistical modelling perspective. The complete system is first presented as a partially observable Markov decision process. The various sub-components are then exposed by introducing appropriate hidden variables. Samples of existing work are then presented within this framework, including dialogue control and optimisation, semantic interpretation, goal detection, natural language generation and synthesis.
If you have difficulty viewing files that end '.gz',
which are gzip compressed, then you may be able to find
tools to uncompress them at the gzip
web site.
If you have difficulty viewing files that are in PostScript, (ending
'.ps' or '.ps.gz'), then you may be able to
find tools to view them at
the gsview
web site.
We have attempted to provide automatically generated PDF copies of documents for which only PostScript versions have previously been available. These are clearly marked in the database - due to the nature of the automatic conversion process, they are likely to be badly aliased when viewed at default resolution on screen by acroread.