srch_WST_graph_t Struct Reference

#include <srch_word_switch_tree.h>

List of all members.

Public Attributes

int32 n_static_lextree
lextree_tcurroottree
lextree_t ** expandtree
lextree_tcurfillertree
lextree_t ** expandfillertree
lextree_t ** roottree
hash_table_t * active_word
glist_t empty_tree_idx_stack
int32 no_active_word
lmset_tlmset
int32 isLMLA
histprune_thistprune

Detailed Description

A note by ARCHAN at 20050703

In general, what made a LVCSR search to be unique has three major factors. They are 1) how high level knowledge source (LM, FSG) is applied, 2) how the lexicon is organized, 3, how cross word triphones is realized and implemented. It is important to realize the interplay between these 3 components to realize how a search actually really works.


Member Data Documentation

Hash table that map word end to the index of the expandtree.

The first filler tree

The first unigram tree that used in the search for this utterance.

Store a pool of indices which indicate a tree is empty. It acts like a stack

The expanded fillertrees

The expanded trees

Structure that wraps up parameters related to

Is LM lookahead used?

The LM set

Number of static lexical tree for word switching

No of active word

The pool of trees that stores all word trees. An array with dimension. #lm


The documentation for this struct was generated from the following file:

Generated on 7 Mar 2010 by  doxygen 1.6.1