PocketSphinx 5prealpha
|
N-Gram search module structure. More...
#include <ngram_search.h>
Data Fields | |
ps_search_t | base |
ngram_model_t * | lmset |
Set of language models. More... | |
hmm_context_t * | hmmctx |
HMM context. More... | |
uint8 | fwdtree |
uint8 | fwdflat |
uint8 | bestpath |
uint8 | done |
listelem_alloc_t * | chan_alloc |
For chan_t. More... | |
listelem_alloc_t * | root_chan_alloc |
For root_chan_t. More... | |
listelem_alloc_t * | latnode_alloc |
For latnode_t. More... | |
root_chan_t * | root_chan |
Search structure of HMM instances. More... | |
int32 | n_root_chan_alloc |
Number of root_chan allocated. More... | |
int32 | n_root_chan |
Number of valid root_chan. More... | |
int32 | n_nonroot_chan |
Number of valid non-root channels. More... | |
int32 | max_nonroot_chan |
Maximum possible number of non-root channels. More... | |
root_chan_t * | rhmm_1ph |
Root HMMs for single-phone words. More... | |
chan_t ** | word_chan |
Channels associated with a given word (only used for right contexts, single-phone words in fwdtree search, and word HMMs in fwdflat search). More... | |
bitvec_t * | word_active |
array of active flags for all words. More... | |
int32 * | homophone_set |
Each node in the HMM tree structure may point to a set of words whose last phone would follow that node in the tree structure (but is not included in the tree structure for reasons explained above). More... | |
int32 * | single_phone_wid |
list of single-phone word ids More... | |
int32 | n_1ph_words |
Number single phone words in dict (total) More... | |
int32 | n_1ph_LMwords |
Number single phone dict words also in LM; these come first in single_phone_wid. More... | |
chan_t *** | active_chan_list |
Array of active channels for current and next frame. More... | |
int32 | n_active_chan [2] |
Number entries in active_chan_list. More... | |
int32 ** | active_word_list |
Array of active multi-phone words for current and next frame. More... | |
int32 | n_active_word [2] |
Number entries in active_word_list. More... | |
lastphn_cand_t * | lastphn_cand |
int32 | n_lastphn_cand |
last_ltrans_t * | last_ltrans |
int32 | cand_sf_alloc |
cand_sf_t * | cand_sf |
bestbp_rc_t * | bestbp_rc |
bptbl_t * | bp_table |
int32 | bpidx |
int32 | bp_table_size |
int32 * | bscore_stack |
int32 | bss_head |
int32 | bscore_stack_size |
int32 | n_frame_alloc |
Number of frames allocated in bp_table_idx and friends. More... | |
int32 | n_frame |
Number of frames actually present. More... | |
int32 * | bp_table_idx |
int32 * | word_lat_idx |
ps_latnode_t ** | frm_wordlist |
List of active words in each frame. More... | |
int32 * | fwdflat_wordlist |
List of active word IDs for utterance. More... | |
bitvec_t * | expand_word_flag |
int32 * | expand_word_list |
int32 | n_expand_words |
int32 | min_ef_width |
int32 | max_sf_win |
float32 | fwdflat_fwdtree_lw_ratio |
int32 | best_score |
Best Viterbi path score. More... | |
int32 | last_phone_best_score |
Best Viterbi path score for last phone. More... | |
int32 | renormalized |
float32 | bestpath_fwdtree_lw_ratio |
float32 | ascale |
Acoustic score scale for posterior probabilities. More... | |
ngram_search_stats_t | st |
Various statistics for profiling. More... | |
ptmr_t | fwdtree_perf |
ptmr_t | fwdflat_perf |
ptmr_t | bestpath_perf |
int32 | n_tot_frame |
int32 | beam |
int32 | dynamic_beam |
int32 | pbeam |
int32 | wbeam |
int32 | lpbeam |
int32 | lponlybeam |
int32 | fwdflatbeam |
int32 | fwdflatwbeam |
int32 | fillpen |
int32 | silpen |
int32 | wip |
int32 | nwpen |
int32 | pip |
int32 | maxwpf |
int32 | maxhmmpf |
N-Gram search module structure.
Definition at line 197 of file ngram_search.h.
chan_t*** ngram_search_s::active_chan_list |
Array of active channels for current and next frame.
In any frame, only some HMM tree nodes are active. active_chan_list[f mod 2] = list of nonroot channels in the HMM tree active in frame f.
Definition at line 275 of file ngram_search.h.
Referenced by ngram_fwdtree_deinit(), and ngram_fwdtree_finish().
int32** ngram_search_s::active_word_list |
Array of active multi-phone words for current and next frame.
Similarly to active_chan_list, active_word_list[f mod 2] = list of word ids for which active channels exist in word_chan in frame f.
Statically allocated single-phone words are always active and should not appear in this list.
Definition at line 287 of file ngram_search.h.
Referenced by ngram_fwdflat_search(), ngram_fwdflat_start(), ngram_fwdtree_finish(), ngram_search_free(), and ngram_search_init().
float32 ngram_search_s::ascale |
Acoustic score scale for posterior probabilities.
Definition at line 333 of file ngram_search.h.
ps_search_t ngram_search_s::base |
Definition at line 198 of file ngram_search.h.
int32 ngram_search_s::beam |
Definition at line 342 of file ngram_search.h.
int32 ngram_search_s::best_score |
Best Viterbi path score.
Definition at line 325 of file ngram_search.h.
Referenced by ngram_fwdflat_search(), ngram_fwdflat_start(), ngram_fwdtree_search(), ngram_fwdtree_start(), and ngram_search_lattice().
bestbp_rc_t* ngram_search_s::bestbp_rc |
Definition at line 298 of file ngram_search.h.
uint8 ngram_search_s::bestpath |
Definition at line 205 of file ngram_search.h.
float32 ngram_search_s::bestpath_fwdtree_lw_ratio |
Definition at line 332 of file ngram_search.h.
ptmr_t ngram_search_s::bestpath_perf |
Definition at line 338 of file ngram_search.h.
bptbl_t* ngram_search_s::bp_table |
Definition at line 300 of file ngram_search.h.
int32* ngram_search_s::bp_table_idx |
Definition at line 309 of file ngram_search.h.
int32 ngram_search_s::bp_table_size |
Definition at line 302 of file ngram_search.h.
int32 ngram_search_s::bpidx |
Definition at line 301 of file ngram_search.h.
int32* ngram_search_s::bscore_stack |
Definition at line 303 of file ngram_search.h.
int32 ngram_search_s::bscore_stack_size |
Definition at line 305 of file ngram_search.h.
int32 ngram_search_s::bss_head |
Definition at line 304 of file ngram_search.h.
cand_sf_t* ngram_search_s::cand_sf |
Definition at line 297 of file ngram_search.h.
int32 ngram_search_s::cand_sf_alloc |
Definition at line 296 of file ngram_search.h.
listelem_alloc_t* ngram_search_s::chan_alloc |
For chan_t.
Definition at line 211 of file ngram_search.h.
Referenced by ngram_search_alloc_all_rc(), ngram_search_free(), ngram_search_free_all_rc(), and ngram_search_init().
uint8 ngram_search_s::done |
Definition at line 208 of file ngram_search.h.
int32 ngram_search_s::dynamic_beam |
Definition at line 343 of file ngram_search.h.
bitvec_t* ngram_search_s::expand_word_flag |
Definition at line 318 of file ngram_search.h.
int32* ngram_search_s::expand_word_list |
Definition at line 319 of file ngram_search.h.
int32 ngram_search_s::fillpen |
Definition at line 350 of file ngram_search.h.
ps_latnode_t** ngram_search_s::frm_wordlist |
List of active words in each frame.
Definition at line 316 of file ngram_search.h.
Referenced by ngram_fwdflat_deinit(), ngram_fwdflat_init(), and ngram_search_mark_bptable().
uint8 ngram_search_s::fwdflat |
Definition at line 204 of file ngram_search.h.
float32 ngram_search_s::fwdflat_fwdtree_lw_ratio |
Definition at line 323 of file ngram_search.h.
ptmr_t ngram_search_s::fwdflat_perf |
Definition at line 337 of file ngram_search.h.
int32* ngram_search_s::fwdflat_wordlist |
List of active word IDs for utterance.
Definition at line 317 of file ngram_search.h.
Referenced by ngram_fwdflat_deinit(), ngram_fwdflat_init(), ngram_fwdflat_reinit(), and ngram_fwdflat_search().
int32 ngram_search_s::fwdflatbeam |
Definition at line 348 of file ngram_search.h.
int32 ngram_search_s::fwdflatwbeam |
Definition at line 349 of file ngram_search.h.
uint8 ngram_search_s::fwdtree |
Definition at line 203 of file ngram_search.h.
ptmr_t ngram_search_s::fwdtree_perf |
Definition at line 336 of file ngram_search.h.
hmm_context_t* ngram_search_s::hmmctx |
HMM context.
Definition at line 200 of file ngram_search.h.
Referenced by ngram_fwdflat_search(), ngram_search_alloc_all_rc(), ngram_search_free(), and ngram_search_init().
int32* ngram_search_s::homophone_set |
Each node in the HMM tree structure may point to a set of words whose last phone would follow that node in the tree structure (but is not included in the tree structure for reasons explained above).
The channel node points to one word in this set of words. The remaining words are linked through homophone_set[].
Single-phone words are not represented in the HMM tree; they are kept in word_chan.
Specifically, homophone_set[w] = wid of next word in the same set as w.
Definition at line 263 of file ngram_search.h.
last_ltrans_t* ngram_search_s::last_ltrans |
Definition at line 295 of file ngram_search.h.
int32 ngram_search_s::last_phone_best_score |
Best Viterbi path score for last phone.
Definition at line 326 of file ngram_search.h.
lastphn_cand_t* ngram_search_s::lastphn_cand |
Definition at line 293 of file ngram_search.h.
listelem_alloc_t* ngram_search_s::latnode_alloc |
For latnode_t.
Definition at line 213 of file ngram_search.h.
Referenced by ngram_search_free(), and ngram_search_init().
ngram_model_t* ngram_search_s::lmset |
Set of language models.
Definition at line 199 of file ngram_search.h.
Referenced by ngram_search_free(), and ngram_search_init().
int32 ngram_search_s::lpbeam |
Definition at line 346 of file ngram_search.h.
int32 ngram_search_s::lponlybeam |
Definition at line 347 of file ngram_search.h.
int32 ngram_search_s::max_nonroot_chan |
Maximum possible number of non-root channels.
Definition at line 235 of file ngram_search.h.
Referenced by ngram_fwdtree_deinit().
int32 ngram_search_s::max_sf_win |
Definition at line 322 of file ngram_search.h.
int32 ngram_search_s::maxhmmpf |
Definition at line 356 of file ngram_search.h.
int32 ngram_search_s::maxwpf |
Definition at line 355 of file ngram_search.h.
int32 ngram_search_s::min_ef_width |
Definition at line 321 of file ngram_search.h.
int32 ngram_search_s::n_1ph_LMwords |
Number single phone dict words also in LM; these come first in single_phone_wid.
Definition at line 266 of file ngram_search.h.
int32 ngram_search_s::n_1ph_words |
Number single phone words in dict (total)
Definition at line 265 of file ngram_search.h.
Referenced by ngram_fwdflat_start(), and ngram_fwdtree_start().
int32 ngram_search_s::n_active_chan[2] |
Number entries in active_chan_list.
Definition at line 276 of file ngram_search.h.
Referenced by ngram_fwdtree_finish(), and ngram_fwdtree_start().
int32 ngram_search_s::n_active_word[2] |
Number entries in active_word_list.
Definition at line 288 of file ngram_search.h.
Referenced by ngram_fwdflat_search(), ngram_fwdflat_start(), ngram_fwdtree_finish(), and ngram_fwdtree_start().
int32 ngram_search_s::n_expand_words |
Definition at line 320 of file ngram_search.h.
int32 ngram_search_s::n_frame |
Number of frames actually present.
Definition at line 308 of file ngram_search.h.
Referenced by ngram_fwdflat_search(), ngram_fwdflat_start(), ngram_fwdtree_search(), ngram_fwdtree_start(), ngram_search_find_exit(), and ngram_search_lattice().
int32 ngram_search_s::n_frame_alloc |
Number of frames allocated in bp_table_idx and friends.
Definition at line 307 of file ngram_search.h.
Referenced by ngram_fwdflat_init(), ngram_search_init(), and ngram_search_mark_bptable().
int32 ngram_search_s::n_lastphn_cand |
Definition at line 294 of file ngram_search.h.
int32 ngram_search_s::n_nonroot_chan |
Number of valid non-root channels.
Definition at line 234 of file ngram_search.h.
int32 ngram_search_s::n_root_chan |
Number of valid root_chan.
Definition at line 233 of file ngram_search.h.
Referenced by ngram_fwdtree_finish().
int32 ngram_search_s::n_root_chan_alloc |
Number of root_chan allocated.
Definition at line 232 of file ngram_search.h.
int32 ngram_search_s::n_tot_frame |
Definition at line 339 of file ngram_search.h.
int32 ngram_search_s::nwpen |
Definition at line 353 of file ngram_search.h.
int32 ngram_search_s::pbeam |
Definition at line 344 of file ngram_search.h.
int32 ngram_search_s::pip |
Definition at line 354 of file ngram_search.h.
int32 ngram_search_s::renormalized |
Definition at line 327 of file ngram_search.h.
root_chan_t* ngram_search_s::rhmm_1ph |
Root HMMs for single-phone words.
Definition at line 236 of file ngram_search.h.
root_chan_t* ngram_search_s::root_chan |
Search structure of HMM instances.
The word triphone sequences (HMM instances) are transformed into tree structures, one tree per unique left triphone in the entire dictionary (actually diphone, since its left context varies dyamically during the search process). The entire set of trees of channels is allocated once and for all during initialization (since dynamic management of active CHANs is time consuming), with one exception: the last phones of words, that need multiple right context modelling, are not maintained in this static structure since there are too many of them and few are active at any time. Instead they are maintained as linked lists of CHANs, one list per word, and each CHAN in this set is allocated only on demand and freed if inactive. Roots of search tree.
Definition at line 231 of file ngram_search.h.
Referenced by ngram_fwdtree_finish().
listelem_alloc_t* ngram_search_s::root_chan_alloc |
For root_chan_t.
Definition at line 212 of file ngram_search.h.
Referenced by ngram_search_free(), and ngram_search_init().
int32 ngram_search_s::silpen |
Definition at line 351 of file ngram_search.h.
int32* ngram_search_s::single_phone_wid |
list of single-phone word ids
Definition at line 264 of file ngram_search.h.
Referenced by ngram_fwdflat_start(), and ngram_fwdtree_start().
ngram_search_stats_t ngram_search_s::st |
Various statistics for profiling.
Definition at line 335 of file ngram_search.h.
Referenced by ngram_fwdflat_finish(), ngram_fwdflat_search(), ngram_fwdflat_start(), ngram_fwdtree_finish(), ngram_fwdtree_search(), and ngram_fwdtree_start().
int32 ngram_search_s::wbeam |
Definition at line 345 of file ngram_search.h.
int32 ngram_search_s::wip |
Definition at line 352 of file ngram_search.h.
bitvec_t* ngram_search_s::word_active |
array of active flags for all words.
Definition at line 247 of file ngram_search.h.
Referenced by ngram_fwdflat_finish(), ngram_fwdflat_search(), ngram_fwdtree_finish(), ngram_search_free(), and ngram_search_init().
chan_t** ngram_search_s::word_chan |
Channels associated with a given word (only used for right contexts, single-phone words in fwdtree search, and word HMMs in fwdflat search).
WARNING: For single-phone words and fwdflat search, this actually contains pointers to root_chan_t, which are allocated using root_chan_alloc. This is a suboptimal state of affairs.
Definition at line 246 of file ngram_search.h.
Referenced by ngram_fwdflat_reinit(), ngram_fwdflat_start(), ngram_fwdtree_finish(), ngram_fwdtree_reinit(), ngram_fwdtree_start(), ngram_search_alloc_all_rc(), ngram_search_free(), ngram_search_free_all_rc(), and ngram_search_init().
int32* ngram_search_s::word_lat_idx |
Definition at line 310 of file ngram_search.h.