All Implemented Interfaces:
Direct Known Subclasses:
Postlex, Postlex, PronunciationModel
This module serves as a post-lexical pronunciation model. Its appropriate place in the module chain is after intonisation. The
target features are taken and fed into decision trees that predict the new pronunciation. A new mary xml is output, with the
difference being that the old pronunciation is replaced by the newly predicted one, and a finer grained xml structure.
Methods inherited from class java.lang.
Object clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
Constructor, stating that the input is of type INTONATION, the output of type ALLOPHONES.
public void startup()
Allow the module to start up, performing whatever is necessary to become operational. After successful completion,
getState() should return MODULE_RUNNING.
protected boolean postlexicalRules(
Optionally, a language-specific subclass can implement any postlexical rules on the document.
token - a <t> element with a syllable and <ph> substructure.
allophoneSet - allophoneSet
Returns: true if something was changed, false otherwise
MaryData process( MaryData d)
This computes a new pronunciation for the elements of some MaryData, that is phonemised.
process InternalModule Parameters:
d - d
Returns: A MaryData object of type
outputType() encapsulating the processing result.
This method just returns its input. Subclasses should override this.
Copyright © 2000–2018 DFKI GmbH. All rights reserved.