libsent/src/voca/voca_load_htkdict.c File Reference

Read word dictionary from a file in HTK format. More...

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

Go to the source code of this file.

Defines

#define PHONEMELEN_STEP 30

Memory allocation step for phoneme sequence.

Functions

char * cycle_triphone (char *p)

Return string of triphone name composed from last 3 call.

char * cycle_triphone_flush ()

Flush the triphone buffer and return the last biphone.

static void add_to_error (WORD_INFO *winfo, char *name)

Add a triphone name to the missing error list in WORD_INFO.

static void callback_list_error (void *x)

Traverse callback function to output a error phone.

static void list_error (WORD_INFO *winfo)

Output all error phones appeared while readin a word dictionary.

void voca_set_stats (WORD_INFO *winfo)

Parse a word dictionary and set the maximum state length per word.

void voca_load_start (WORD_INFO *winfo, HTK_HMM_INFO *hmminfo, boolean ignore_tri_conv)

Start loading a dictionary.

boolean voca_load_line (char *buf, WORD_INFO *winfo, HTK_HMM_INFO *hmminfo)

Load a line from buffer and set parameters to the dictionary.

boolean voca_load_end (WORD_INFO *winfo)

End loading dictionary entries.

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 (gzip enabled).

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

Top function to read word dictionary via normal file pointer.

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.

boolean voca_load_htkdict_line (char *buf, WORD_ID *vnum_p, int linenum, 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.

boolean voca_mono2tri (WORD_INFO *winfo, HTK_HMM_INFO *hmminfo)

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

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

Append one word dictionary to other, for multiple grammar handling.

Variables

static char buf [MAXLINELEN]

Local work area for input text processing.

static char bufbak [MAXLINELEN]

Local work area for debug message.

static char trbuf [3][20]

Local buffer for triphone convertion.

static char chbuf [30]

Another local buffer for triphone convertion.

static char nophone [1]

Local buffer to indicate 'no phone'.

static int trp_l

Triphone cycle index.

static int trp

Triphone cycle index.

static int trp_r

Triphone cycle index.

Detailed Description

Read word dictionary from a file in HTK format.

When using triphone model, conversion from monophone expression in dictionary to triphone and the existence check of word-internal triphone will be done here.

Author:: Akinobu LEE

Date:: Fri Feb 18 19:43:06 2005

Revision: 1.7

Definition in file voca_load_htkdict.c.

Function Documentation

char* cycle_triphone ( char * p )

Return string of triphone name composed from last 3 call.

Parameters:

[in] next phone string

Returns:: the composed triphone name, or NULL on end.

Definition at line 80 of file voca_load_htkdict.c.

Referenced by cycle_triphone_flush(), voca_load_htkdict_line(), voca_load_wordlist_line(), and voca_mono2tri().

char* cycle_triphone_flush ( )

Flush the triphone buffer and return the last biphone.

Returns:: the composed last bi-phone name.

Definition at line 126 of file voca_load_htkdict.c.

Referenced by voca_load_htkdict_line(), voca_load_wordlist_line(), and voca_mono2tri().

static void add_to_error	(	WORD_INFO *	winfo,
		char *	name
	)			`[static]`

Add a triphone name to the missing error list in WORD_INFO.

Parameters:

	winfo	[i/o] word dictionary to add the error phone to error list
	name	[in] phone name to be added

Definition at line 138 of file voca_load_htkdict.c.

static void callback_list_error ( void * x ) [static]

Traverse callback function to output a error phone.

Parameters:

[in] error phone string of the node

Definition at line 161 of file voca_load_htkdict.c.

Referenced by list_error().

static void list_error ( WORD_INFO * winfo ) [static]

Output all error phones appeared while readin a word dictionary.

Parameters:

winfo

[in] word dictionary data

Definition at line 173 of file voca_load_htkdict.c.

Referenced by voca_load_end().

void voca_set_stats ( WORD_INFO * winfo )

Parse a word dictionary and set the maximum state length per word.

Parameters:

winfo

[i/o]

Definition at line 186 of file voca_load_htkdict.c.

Referenced by voca_load_end().

void voca_load_start	(	WORD_INFO *	winfo,
		HTK_HMM_INFO *	hmminfo,
		boolean	ignore_tri_conv
	)

Start loading a dictionary.

See voca_load_htkdict() for an example of using this function.

Parameters:

	winfo	[i/o] dictionary data where the data will be loaded
	hmminfo	[in] phoneme HMM definition
	ignore_tri_conv	[in] if TRUE, skip triphone conversion while loading

Definition at line 228 of file voca_load_htkdict.c.

Referenced by voca_load_htkdict(), voca_load_htkdict_fp(), voca_load_wordlist(), and voca_load_wordlist_fp().

boolean voca_load_line	(	char *	buf,
		WORD_INFO *	winfo,
		HTK_HMM_INFO *	hmminfo
	)

Load a line from buffer and set parameters to the dictionary.

See voca_load_htkdict() for an example of using this function.

Parameters:

	buf	[in] input buffer containing a word entry
	winfo	[i/o] word dictionary to append the entry
	hmminfo	[in] phoneme HMM definition

Returns:: TRUE when successfully read, or FALSE on encountered end of dictionary. When an error occurs, this function will set winfo->ok_flag to FALSE.

Definition at line 255 of file voca_load_htkdict.c.

Referenced by voca_append_htkdict(), voca_load_htkdict(), and voca_load_htkdict_fp().

boolean voca_load_end ( WORD_INFO * winfo )

End loading dictionary entries.

It calculates some statistics for the read entries, outputs errors if encountered while the last loading, and returns with status whether an error occured while loading.

Parameters:

winfo

[i/o] word dictionary just read by voca_load_line() calls

Returns:: TRUE when no error has been occured during loading, or FALSE if an error occured.

Definition at line 284 of file voca_load_htkdict.c.

Referenced by voca_append_htkdict(), voca_load_htkdict(), voca_load_htkdict_fp(), voca_load_wordlist(), and voca_load_wordlist_fp().

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 (gzip enabled).

Parameters:

	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

Returns:: TRUE on success, FALSE on any error word.

Definition at line 305 of file voca_load_htkdict.c.

Referenced by init_voca().

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

Top function to read word dictionary via normal file pointer.

Parameters:

	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

Returns:: TRUE on success, FALSE on any error word.

Definition at line 330 of file voca_load_htkdict.c.

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.

Parameters:

	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

Returns:: TRUE on success, FALSE on any error word.

Definition at line 354 of file voca_load_htkdict.c.

Referenced by initialize_dict().

boolean voca_load_htkdict_line	(	char *	buf,
		WORD_ID *	vnum_p,
		int	linenum,
		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.

Parameters:

	buf	[i/o] buffer to hold the input string, will be modified in this function
	vnum_p	[in] current number of words in winfo
	linenum	[in] current line number of the input
	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.

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

Definition at line 374 of file voca_load_htkdict.c.

Referenced by voca_load_line().

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.

Parameters:

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

Returns:: TRUE on success, FALSE on failure.

Definition at line 601 of file voca_load_htkdict.c.

boolean 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.

Parameters:

	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

Definition at line 642 of file voca_load_htkdict.c.

Referenced by multigram_add_words_to_grammar(), multigram_append_to_global(), and multigram_update().

Generated on Thu Jul 23 12:14:20 2009 for Julius by

1.5.1


Defines
#define	PHONEMELEN_STEP 30
	Memory allocation step for phoneme sequence.
Functions
char *	cycle_triphone (char *p)
	Return string of triphone name composed from last 3 call.
char *	cycle_triphone_flush ()
	Flush the triphone buffer and return the last biphone.
static void	add_to_error (WORD_INFO winfo, char name)
	Add a triphone name to the missing error list in WORD_INFO.
static void	callback_list_error (void *x)
	Traverse callback function to output a error phone.
static void	list_error (WORD_INFO *winfo)
	Output all error phones appeared while readin a word dictionary.
void	voca_set_stats (WORD_INFO *winfo)
	Parse a word dictionary and set the maximum state length per word.
void	voca_load_start (WORD_INFO winfo, HTK_HMM_INFO hmminfo, boolean ignore_tri_conv)
	Start loading a dictionary.
boolean	voca_load_line (char buf, WORD_INFO winfo, HTK_HMM_INFO *hmminfo)
	Load a line from buffer and set parameters to the dictionary.
boolean	voca_load_end (WORD_INFO *winfo)
	End loading dictionary entries.
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 (gzip enabled).
boolean	voca_load_htkdict_fp (FILE fp, WORD_INFO winfo, HTK_HMM_INFO *hmminfo, boolean ignore_tri_conv)
	Top function to read word dictionary via normal file pointer.
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.
boolean	voca_load_htkdict_line (char buf, WORD_ID vnum_p, int linenum, 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.
boolean	voca_mono2tri (WORD_INFO winfo, HTK_HMM_INFO hmminfo)
	Convert whole words in word dictionary to word-internal triphone.
boolean	voca_append (WORD_INFO dstinfo, WORD_INFO srcinfo, int coffset, int woffset)
	Append one word dictionary to other, for multiple grammar handling.
Variables
static char	buf [MAXLINELEN]
	Local work area for input text processing.
static char	bufbak [MAXLINELEN]
	Local work area for debug message.
static char	trbuf [3][20]
	Local buffer for triphone convertion.
static char	chbuf [30]
	Another local buffer for triphone convertion.
static char	nophone [1]
	Local buffer to indicate 'no phone'.
static int	trp_l
	Triphone cycle index.
static int	trp
	Triphone cycle index.
static int	trp_r
	Triphone cycle index.