libsent/include/sent/vocabulary.h

単語辞書の構造体定義 [詳細]

#include <sent/stddefs.h>
#include <sent/htk_hmm.h>

vocabulary.hのインクルード依存関係図

このグラフは、どのファイルから直接、間接的にインクルードされているかを示しています。

データ構造
struct	WORD_INFO
	Word dictionary structure to hold vocabulary. [詳細]
マクロ定義
#define	BEGIN_WORD_DEFAULT "<s>"
	Default word string of beginning-of-sentence word.
#define	END_WORD_DEFAULT "</s>"
	Default word string of end-of-sentence word.
#define	MAXWSTEP 4000
	Memory allocation step in number of words when loading a word dictionary.
関数
WORD_INFO *	word_info_new ()
void	word_info_free (WORD_INFO *winfo)
void	winfo_init (WORD_INFO *winfo)
void	winfo_expand (WORD_INFO *winfo)
boolean	init_voca (WORD_INFO winfo, char filename, HTK_HMM_INFO *hmminfo, boolean, boolean)
boolean	voca_load_htkdict (FILE , WORD_INFO , HTK_HMM_INFO *, boolean)
boolean	voca_load_htkdict_fd (int, WORD_INFO , HTK_HMM_INFO , boolean)
boolean	voca_load_htkdict_sd (int, WORD_INFO , HTK_HMM_INFO , boolean)
boolean	voca_append_htkdict (char entry, WORD_INFO winfo, HTK_HMM_INFO *hmminfo, boolean ignore_tri_conv)
void	voca_append (WORD_INFO dstinfo, WORD_INFO srcinfo, int coffset, int woffset)
boolean	voca_load_htkdict_line (char buf, int vnum, WORD_INFO winfo, HTK_HMM_INFO hmminfo, boolean do_conv, boolean ok_flag)
boolean	voca_mono2tri (WORD_INFO winfo, HTK_HMM_INFO hmminfo)
	Convert whole words in word dictionary to word-internal triphone.
WORD_ID	voca_lookup_wid (char , WORD_INFO )
WORD_ID *	new_str2wordseq (WORD_INFO , char , int *)
char *	cycle_triphone (char *p)
char *	cycle_triphone_flush ()
void	print_voca_info (WORD_INFO *)
void	put_voca (WORD_INFO *winfo, WORD_ID wid)
void	put_voca_err (WORD_INFO *winfo, WORD_ID wid)
void	make_base_phone (HTK_HMM_INFO hmminfo, WORD_INFO winfo)
	Build basephone information.
void	print_phone_info (HTK_HMM_INFO *hmminfo)
void	print_all_basephone_detail (HMM_basephone *base)
void	print_all_basephone_name (HMM_basephone *base)
void	test_interword_triphone (HTK_HMM_INFO hmminfo, WORD_INFO winfo)

説明

単語辞書の構造体定義

作者:: Akinobu LEE

日付:: Sat Feb 12 12:38:13 2005

このファイルは認識で用いられる単語辞書を定義します．単語辞書は単語の読み，出力文字列，音素列の他に，文の開始・終了単語や透過単語情報も保持します．

N-gramに出現する語彙の辞書は NGRAM_INFO に格納され，この認識用単語辞書とは区別されることに注意して下さい．単語辞書からN-gramの語彙へのマッピングは WORD_INFO 内の wton[] によって行なわれます．またDFAの場合，wton はその単語が属するDFA_INFO 内のカテゴリ番号を含みます．

Revision: 1.4

vocabulary.h で定義されています。

関数

WORD_INFO* word_info_new ( )

Allocate a new word dictionary structure.

戻り値:: pointer to the newly allocated WORD_INFO.

voca_malloc.c の 34 行で定義されています。

参照元 initialize_dict(), multigram_exec(), と multigram_read_file().

void word_info_free ( WORD_INFO * winfo )

Free all informations in the WORD_INFO.

引数:

winfo

[i/o] word dictionary data to be freed.

voca_malloc.c の 50 行で定義されています。

参照元 multigram_exec(), と multigram_exec_delete().

void winfo_init ( WORD_INFO * winfo )

Initialize a new word dictionary structure.

引数:

winfo

[i/o] word dictionary to be initialized.

voca_malloc.c の 75 行で定義されています。

参照元 multigram_exec(), voca_load_htkdict(), voca_load_htkdict_fd(), と voca_load_htkdict_sd().

void winfo_expand ( WORD_INFO * winfo )

Expand the word dictionary.

引数:

winfo

[i/o] word dictionary to be expanded.

voca_malloc.c の 105 行で定義されています。

参照元 voca_append(), voca_append_htkdict(), voca_load_htkdict(), voca_load_htkdict_fd(), と voca_load_htkdict_sd().

boolean init_voca	(	WORD_INFO *	winfo,
		char *	filename,
		HTK_HMM_INFO *	hmminfo,
		boolean	not_conv_tri,
		boolean	force_dict
	)

Load and initialize a word dictionary.

引数:

	winfo	[out] pointer to a word dictionary data to store the read data
	filename	[in] file name of the word dictionary to read
	hmminfo	[in] HMM definition data, needed for triphone conversion.
	not_conv_tri	[in] TRUE if not converting monophone to triphone.
	force_dict	[in] TRUE if want to ignore the error words in the dictionary

戻り値:: TRUE on success, FALSE on failure.

init_voca.c の 40 行で定義されています。

参照元 initialize_dict(), と multigram_read_file().

boolean voca_load_htkdict	(	FILE *	fp,
		WORD_INFO *	winfo,
		HTK_HMM_INFO *	hmminfo,
		boolean	ignore_tri_conv
	)

Top function to read word dictionary via file pointer

引数:

	fp	[in] file pointer
	winfo	[out] pointer to word dictionary to store the read data.
	hmminfo	[in] HTK HMM definition data. if NULL, phonemes are ignored.
	ignore_tri_conv	[in] TRUE if triphone conversion is ignored

戻り値:: TRUE on success, FALSE on any error word.

voca_load_htkdict.c の 229 行で定義されています。

参照元 init_voca().

boolean voca_load_htkdict_fd	(	int	fd,
		WORD_INFO *	winfo,
		HTK_HMM_INFO *	hmminfo,
		boolean	ignore_tri_conv
	)

Top function to read word dictionary via file descriptor.

引数:

	fd	[in] file descriptor
	winfo	[out] pointer to word dictionary to store the read data.
	hmminfo	[in] HTK HMM definition data. if NULL, phonemes are ignored.
	ignore_tri_conv	[in] TRUE if triphone conversion is ignored

戻り値:: TRUE on success, FALSE on any error word.

voca_load_htkdict.c の 269 行で定義されています。

boolean voca_load_htkdict_sd	(	int	sd,
		WORD_INFO *	winfo,
		HTK_HMM_INFO *	hmminfo,
		boolean	ignore_tri_conv
	)

Top function to read word dictionary via socket descriptor.

引数:

	sd	[in] socket descriptor
	winfo	[out] pointer to word dictionary to store the read data.
	hmminfo	[in] HTK HMM definition data. if NULL, phonemes are ignored.
	ignore_tri_conv	[in] TRUE if triphone conversion is ignored

戻り値:: TRUE on success, FALSE on any error word.

voca_load_htkdict.c の 308 行で定義されています。

boolean voca_append_htkdict	(	char *	entry,
		WORD_INFO *	winfo,
		HTK_HMM_INFO *	hmminfo,
		boolean	ignore_tri_conv
	)

Append a single entry to the existing word dictionary.

引数:

	entry	[in] dictionary entry string to be appended.
	winfo	[out] pointer to word dictionary to append the data.
	hmminfo	[in] HTK HMM definition data. if NULL, phonemes are ignored.
	ignore_tri_conv	[in] TRUE if triphone conversion is ignored

戻り値:: TRUE on success, FALSE on any error word.

voca_load_htkdict.c の 347 行で定義されています。

参照元 initialize_dict().

void voca_append	(	WORD_INFO *	dstinfo,
		WORD_INFO *	srcinfo,
		int	coffset,
		int	woffset
	)

Append one word dictionary to other, for multiple grammar handling. Assumes that the same HMM definition is used on both word dictionary.

引数:

	dstinfo	[i/o] word dictionary
	srcinfo	[in] word dictionary to be appended to dst
	coffset	[in] category id offset in dst where the new data should be stored
	woffset	[in] word id offset in dst where the new data should be stored

voca_load_htkdict.c の 637 行で定義されています。

参照元 multigram_build_append().

boolean voca_load_htkdict_line	(	char *	buf,
		int	vnum,
		WORD_INFO *	winfo,
		HTK_HMM_INFO *	hmminfo,
		boolean	do_conv,
		boolean *	ok_flag
	)

Sub function to Add a dictionary entry line to the word dictionary.

引数:

	buf	[i/o] buffer to hold the input string, will be modified in this function
	vnum	[in] current number of words in winfo
	winfo	[out] pointer to word dictionary to append the data.
	hmminfo	[in] HTK HMM definition data. if NULL, phonemes are ignored.
	do_conv	[in] TRUE if performing triphone conversion
	ok_flag	[out] will be set to FALSE if an error occured for this input.

戻り値:: FALSE if buf == "DICEND", else TRUE will be returned.

voca_load_htkdict.c の 384 行で定義されています。

参照元 voca_append_htkdict(), voca_load_htkdict(), voca_load_htkdict_fd(), と voca_load_htkdict_sd().

boolean voca_mono2tri	(	WORD_INFO *	winfo,
		HTK_HMM_INFO *	hmminfo
	)

Convert whole words in word dictionary to word-internal triphone.

Normally triphone conversion will be performed directly when reading dictionary file. This function is for post conversion only.

引数:

	winfo	[i/o] word dictionary information
	hmminfo	[in] HTK HMM definition

戻り値:: TRUE on success, FALSE on failure.

voca_load_htkdict.c の 596 行で定義されています。

参照元 final_fusion().

WORD_ID voca_lookup_wid	(	char *	keyword,
		WORD_INFO *	winfo
	)

Look up a word on dictionary by string.

引数:

	keyword	[in] keyword to search
	winfo	[in] word dictionary

戻り値:: the word id if found, or WORD_INVALID if not found.

voca_lookup.c の 42 行で定義されています。

参照元 initialize_dict(), と new_str2wordseq().

WORD_ID* new_str2wordseq	(	WORD_INFO *	winfo,
		char *	s,
		int *	len_return
	)

Convert string of space-separated word strings to array of word ids.

引数:

	winfo	[in] word dictionary
	s	[in] string of space-separated word strings
	len_return	[out] number of found words

戻り値:: pointer to a newly allocated word list.

voca_lookup.c の 116 行で定義されています。

char* cycle_triphone ( char * p )

Return string of triphone name composed from last 3 call.

引数:

p

[in] next phone string

戻り値:: the composed triphone name, or NULL on end.

voca_load_htkdict.c の 79 行で定義されています。

参照元 cycle_triphone_flush(), new_str2phseq(), voca_load_htkdict_line(), と voca_mono2tri().

char* cycle_triphone_flush ( )

Flush the triphone buffer and return the last biphone.

戻り値:: the composed last bi-phone name.

voca_load_htkdict.c の 125 行で定義されています。

参照元 new_str2phseq(), voca_load_htkdict_line(), と voca_mono2tri().

void print_voca_info ( WORD_INFO * winfo )

Output overall word dictionary information to stdout.

引数:

winfo

[in] word dictionary

voca_util.c の 33 行で定義されています。

参照元 print_info().

void put_voca	(	WORD_INFO *	winfo,
		WORD_ID	wid
	)

Output information of a word in dictionary to stdout.

引数:

	winfo	[in] word dictionary
	wid	[in] word id to be output

voca_util.c の 80 行で定義されています。

参照元 hmm_check(), make_dfa_voca_ref(), print_info(), と wchmm_add_word().

void put_voca_err	(	WORD_INFO *	winfo,
		WORD_ID	wid
	)

Output information of a word in dictionary to stderr.

引数:

	winfo	[in] word dictionary
	wid	[in] word id to be output

voca_util.c の 113 行で定義されています。

void make_base_phone	(	HTK_HMM_INFO *	hmminfo,
		WORD_INFO *	winfo
	)

Build basephone information.

Extract base phones from HMM definition, mark them whether they appear on word head or word tail, and count the number.

引数:

	hmminfo	[i/o] HMM definition information, basephone list will be added.
	winfo	[in] word dictionary information

chkhmmlist.c の 381 行で定義されています。

参照元 hmm_check().

void print_phone_info ( HTK_HMM_INFO * hmminfo )

Output general information concerning phone mapping in HMM definition.

引数:

hmminfo

[in] HMM definition data.

chkhmmlist.c の 395 行で定義されています。

参照元 hmm_check().

void print_all_basephone_detail ( HMM_basephone * base )

Output all basephone informations to stdout.

引数:

base

[in] pointer to the top basephone data holder.

chkhmmlist.c の 105 行で定義されています。

参照元 hmm_check().

void print_all_basephone_name ( HMM_basephone * base )

Output all basephone names to stdout

引数:

base

[in] pointer to the top basephone data holder.

chkhmmlist.c の 115 行で定義されています。

参照元 hmm_check().

void test_interword_triphone	(	HTK_HMM_INFO *	hmminfo,
		WORD_INFO *	winfo
	)

Top function to check if all the possible triphones on given word dictionary actually exist in the logical HMM.

引数:

	hmminfo	[in] HMM definition information, with basephone list.
	winfo	[in] word dictionary information

chkhmmlist.c の 340 行で定義されています。

参照元 hmm_check().

libsent/include/sent/vocabulary.h

データ構造

マクロ定義

関数

説明

関数