| Document Type
|
:
|
BL
|
| Record Number
|
:
|
666066
|
| Doc. No
|
:
|
dltt
|
| Main Entry
|
:
|
Thomson, Blaise
|
| Title & Author
|
:
|
Statistical methods for spoken dialogue management\ Blaise Thomson
|
| Publication Statement
|
:
|
London :: Springer,, 2013
|
| Series Statement
|
:
|
Springer Theses
|
| Page. NO
|
:
|
1 online resource (141 p.)
|
| ISBN
|
:
|
9781447149231 (electronic bk.)
|
|
|
:
|
: 1447149238 (electronic bk.)
|
|
|
:
|
9781447149224
|
| Notes
|
:
|
"Doctoral thesis accepted by University of Cambridge, UK."--t.p
|
| Bibliographies/Indexes
|
:
|
Includes bibliographical references and index
|
| Contents
|
:
|
Dialogue System Theory -- Maintaining State -- Maintaining State: Optimisations -- Policy design -- Evaluation -- Parameter learning
|
| Abstract
|
:
|
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
|
| Subject
|
:
|
Speech processing systems
|
| Subject
|
:
|
Discourse analysis
|
| Dewey Classification
|
:
|
006.3/5
|
|
|
:
|
400
|
| LC Classification
|
:
|
P95.3
|
|
|
:
|
P95.3
|
| Added Entry
|
:
|
Ohio Library and Information Network
|