構造体 Sentence

Output result structure [詳細]

#include <recog.h>

Sentenceのコラボレーション図

Collaboration graph
[凡例]

変数

WORD_ID word [MAXSEQNUM]
 Sequence of word ID
int word_num
 Number of words in the sentence
LOGPROB score
 Likelihood (LM+AM)
LOGPROB confidence [MAXSEQNUM]
 Word confidence scores
LOGPROB score_lm
 Language model likelihood (scaled) for N-gram
LOGPROB score_am
 Acoustic model likelihood for N-gram
int gram_id
 The grammar ID this sentence belongs to for DFA
struct {
   boolean   filled
 True if has data
   int   num
 Number of units
   short   unittype
 Unit type (one of PER_*)
   WORD_ID *   w
 word sequence by id (PER_WORD)
   HMM_Logical **   ph
 Phone sequence (PER_PHONEME, PER_STATE)
   short *   loc
 sequence of state location in a phone (PER_STATE)
   boolean *   is_iwsp
 TRUE if PER_STATE and this is the inter-word pause state at multipath mode
   int *   begin_frame
 List of beginning frame
   int *   end_frame
 List of ending frame
   LOGPROB *   avgscore
 Score averaged by frames
   LOGPROB   allscore
 Re-computed acoustic score
align

説明

Output result structure

recog.h283 行で定義されています。


この構造体の説明は次のファイルから生成されました:
Juliusに対してTue Dec 18 16:05:26 2007に生成されました。  doxygen 1.5.4