void
vithist_rescore(vithist_t * vh, ngram_model_t *lm,
s3dict_t *dict, dict2pid_t *dict2pid,
fillpen_t *fp,
s3wid_t wid, int32 ef, int32 score,
int32 pred, int32 type, int32 rc)
{
vithist_entry_t *pve, tve;
int32 lwid;
int32 se, fe;
int32 i;
assert(vh->n_frm == ef);
if (pred == -1) {
/* Always do E_FATAL assuming upper level function take care of error checking. */
E_FATAL
("Hmm->out.history equals to -1 with score %d, some active phone was not computed?\n",
score);
}
/* pve is the previous entry before word with wid or, se an fe is the
first to the last entry before pve. So pve is w_{n-1} */
pve = vithist_id2entry(vh, pred);
/* Create a temporary entry with all the info currently available */
tve.wid = wid;
tve.sf = pve->ef + 1;
tve.ef = ef;
tve.type = type;
tve.valid = 1;
tve.ascr = score - pve->path.score;
tve.lscr = 0;
tve.rc = NULL;
tve.n_rc = 0;
/* Filler words only have unigram language model scores, so not
* much special needs to be done for them. vithist_prune() is
* going to prune out most of these later on, anyway. */
if (s3dict_filler_word(dict, wid)) {
tve.path.score = score;
tve.lscr = fillpen(fp, wid);
tve.path.score += tve.lscr;
if ((tve.path.score - vh->wbeam) >= vh->bestscore[vh->n_frm]) {
tve.path.pred = pred;
/* Note that they just propagate the same LM state since
* they are not in the LM. */
tve.lmstate.lm3g = pve->lmstate.lm3g;
vithist_enter(vh, dict, dict2pid, &tve, rc);
}
}
else {
if (pred == 0) { /* Special case for the initial <s> entry */
se = 0;
fe = 1;
}
else {
se = vh->frame_start[pve->ef];
fe = vh->frame_start[pve->ef + 1];
}
/* Now if it is a word, backtrack again to get all possible previous word
So pve becomes the w_{n-2}.
*/
lwid = ngram_wid(lm, s3dict_wordstr(dict, s3dict_basewid(dict, wid)));
tve.lmstate.lm3g.lwid[0] = lwid;
/* FIXME: This loop is completely awful. For each entry in
* this frame, we scan every entry in the previous frame,
* potentially creating a new history entry. This means that
* without pruning, the size of the vithist table (and thus
* the time taken here) is exponential in the number of
* frames! */
for (i = se; i < fe; i++) {
pve = vithist_id2entry(vh, i);
if (pve->valid) {
int n_used;
tve.path.score = pve->path.score + tve.ascr;
/* Try at all costs to avoid calling ngram_tg_score()
* because it is the main time consuming part here
* (but as noted above... ugh...) See below as well. */
if ((tve.path.score - vh->wbeam) < vh->bestscore[vh->n_frm])
continue;
/* The trigram cache is supposed to make this fast,
* but due to the crazy number of times this could be
* called, it's still slow compared to a hash
* table. */
tve.lscr = ngram_tg_score(lm, lwid, pve->lmstate.lm3g.lwid[0],
pve->lmstate.lm3g.lwid[1], &n_used);
tve.path.score += tve.lscr;
/* A different word exit threshold - we would have to
* be inside the general word beam in order to get
* here, now we apply a second beam to the *vithist
* entries* in this frame. There can be an ungodly
* number of them for reasons that aren't entirely
* clear to me, so this is kind of a pre-pruning.
* NOTE: the "backwards" math here is because
* vh->bestscore is frequently MAX_NEG_INT32. ALSO
* NOTE: We can't precompute the threshold since the
* best score will be updated by vithist_enter(). */
if ((tve.path.score - vh->wbeam) >= vh->bestscore[vh->n_frm]) {
tve.path.pred = i;
tve.lmstate.lm3g.lwid[1] = pve->lmstate.lm3g.lwid[0];
vithist_enter(vh, dict, dict2pid, &tve, rc);
}
}
}
}
}
void
run_tests(logmath_t *lmath, ngram_model_t *model)
{
int32 rv, i;
TEST_ASSERT(model);
TEST_EQUAL(ngram_wid(model, "scylla"), 285);
TEST_EQUAL(strcmp(ngram_word(model, 285), "scylla"), 0);
rv = ngram_model_read_classdef(model, LMDIR "/100.probdef");
TEST_EQUAL(rv, 0);
/* Verify that class word IDs remain the same. */
TEST_EQUAL(ngram_wid(model, "scylla"), 285);
TEST_EQUAL(strcmp(ngram_word(model, 285), "scylla"), 0);
/* Verify in-class word IDs. */
TEST_EQUAL(ngram_wid(model, "scylla:scylla"), 0x80000000 | 400);
/* Verify in-class and out-class unigram scores. */
TEST_EQUAL_LOG(ngram_score(model, "scylla:scylla", NULL),
logmath_log10_to_log(lmath, -2.7884) + logmath_log(lmath, 0.4));
TEST_EQUAL_LOG(ngram_score(model, "scooby:scylla", NULL),
logmath_log10_to_log(lmath, -2.7884) + logmath_log(lmath, 0.1));
TEST_EQUAL_LOG(ngram_score(model, "scylla", NULL),
logmath_log10_to_log(lmath, -2.7884));
TEST_EQUAL_LOG(ngram_score(model, "oh:zero", NULL),
logmath_log10_to_log(lmath, -1.9038) + logmath_log(lmath, 0.7));
TEST_EQUAL_LOG(ngram_score(model, "zero", NULL),
logmath_log10_to_log(lmath, -1.9038));
/* Verify class bigram scores. */
TEST_EQUAL_LOG(ngram_score(model, "scylla", "on", NULL),
logmath_log10_to_log(lmath, -1.2642));
TEST_EQUAL_LOG(ngram_score(model, "scylla:scylla", "on", NULL),
logmath_log10_to_log(lmath, -1.2642) + logmath_log(lmath, 0.4));
TEST_EQUAL_LOG(ngram_score(model, "apparently", "scylla", NULL),
logmath_log10_to_log(lmath, -0.5172));
TEST_EQUAL_LOG(ngram_score(model, "apparently", "karybdis:scylla", NULL),
logmath_log10_to_log(lmath, -0.5172));
TEST_EQUAL_LOG(ngram_score(model, "apparently", "scooby:scylla", NULL),
logmath_log10_to_log(lmath, -0.5172));
/* Verify class trigram scores. */
TEST_EQUAL_LOG(ngram_score(model, "zero", "be", "will", NULL),
logmath_log10_to_log(lmath, -0.5725));
TEST_EQUAL_LOG(ngram_score(model, "oh:zero", "be", "will", NULL),
logmath_log10_to_log(lmath, -0.5725) + logmath_log(lmath, 0.7));
TEST_EQUAL_LOG(ngram_score(model, "should", "variance", "zero", NULL),
logmath_log10_to_log(lmath, -0.9404));
TEST_EQUAL_LOG(ngram_score(model, "should", "variance", "zero:zero", NULL),
logmath_log10_to_log(lmath, -0.9404));
/* Add words to classes. */
rv = ngram_model_add_class_word(model, "scylla", "scrappy:scylla", 1.0);
TEST_ASSERT(rv >= 0);
TEST_EQUAL(ngram_wid(model, "scrappy:scylla"), 0x80000196);
TEST_EQUAL_LOG(ngram_score(model, "scrappy:scylla", NULL),
logmath_log10_to_log(lmath, -2.7884) + logmath_log(lmath, 0.2));
printf("scrappy:scylla %08x %d %f\n",
ngram_wid(model, "scrappy:scylla"),
ngram_score(model, "scrappy:scylla", NULL),
logmath_exp(lmath, ngram_score(model, "scrappy:scylla", NULL)));
/* Add a lot of words to a class. */
for (i = 0; i < 129; ++i) {
char word[32];
sprintf(word, "%d:scylla", i);
rv = ngram_model_add_class_word(model, "scylla", word, 1.0);
printf("%s %08x %d %f\n", word,
ngram_wid(model, word),
ngram_score(model, word, NULL),
logmath_exp(lmath, ngram_score(model, word, NULL)));
TEST_ASSERT(rv >= 0);
TEST_EQUAL(ngram_wid(model, word), 0x80000197 + i);
}
/* Add a new class. */
{
const char *words[] = { "blatz:foobie", "hurf:foobie" };
float32 weights[] = { 0.6, 0.4 };
int32 foobie_prob;
rv = ngram_model_add_class(model, "[foobie]", 1.0,
words, weights, 2);
TEST_ASSERT(rv >= 0);
foobie_prob = ngram_score(model, "[foobie]", NULL);
TEST_EQUAL_LOG(ngram_score(model, "blatz:foobie", NULL),
foobie_prob + logmath_log(lmath, 0.6));
TEST_EQUAL_LOG(ngram_score(model, "hurf:foobie", NULL),
foobie_prob + logmath_log(lmath, 0.4));
}
}
char *
dict_g2p(char const *word_grapheme, ngram_model_t *ngram_g2p_model)
{
char *final_phone = NULL;
int totalh = 0;
size_t increment = 1;
int word_offset = 0;
int j;
size_t grapheme_len = 0, final_phoneme_len = 0;
glist_t history_list = NULL;
gnode_t *gn;
int first = 0;
const int32 *total_unigrams;
struct winner_t winner;
const char *word;
unigram_t unigram;
total_unigrams = ngram_model_get_counts(ngram_g2p_model);
int32 wid_sentence = ngram_wid(ngram_g2p_model,"<s>"); // start with sentence
history_list = glist_add_int32(history_list, wid_sentence);
grapheme_len = strlen(word_grapheme);
for (j = 0; j < grapheme_len; j += increment) {
winner = dict_get_winner_wid(ngram_g2p_model, word_grapheme, history_list, *total_unigrams, word_offset);
increment = winner.length_match;
if (increment == 0) {
E_ERROR("Error trying to find matching phoneme (%s) Exiting.. \n" , word_grapheme);
return NULL;
}
history_list = glist_add_int32(history_list, winner.winner_wid);
totalh = j + 1;
word_offset += winner.length_match;
final_phoneme_len += winner.len_phoneme;
}
history_list = glist_reverse(history_list);
final_phone = ckd_calloc(1, final_phoneme_len * 2);
for (gn = history_list; gn; gn = gnode_next(gn)) {
if (!first) {
first = 1;
continue;
}
word = ngram_word(ngram_g2p_model, gnode_int32(gn));
if (!word)
continue;
unigram = dict_split_unigram(word);
if (strcmp(unigram.phone, "_") == 0) {
if (unigram.word)
ckd_free(unigram.word);
if (unigram.phone)
ckd_free(unigram.phone);
continue;
}
strcat(final_phone, unigram.phone);
strcat(final_phone, " ");
if (unigram.word)
ckd_free(unigram.word);
if (unigram.phone)
ckd_free(unigram.phone);
}
if (history_list)
glist_free(history_list);
return final_phone;
}
void
run_tests(ngram_model_t *model)
{
int32 n_used;
ngram_tg_score(model,
ngram_wid(model, "daines"),
ngram_wid(model, "huggins"),
ngram_wid(model, "huggins"), &n_used);
TEST_EQUAL(n_used, 2);
ngram_tg_score(model,
ngram_wid(model, "david"),
ngram_wid(model, "david"),
ngram_wid(model, "david"), &n_used);
TEST_EQUAL(n_used, 1);
/* Apply weights. */
ngram_model_apply_weights(model, 7.5, 0.5, 1.0);
/* -9452 * 7.5 + log(0.5) = -77821 */
TEST_EQUAL_LOG(ngram_score(model, "daines", "huggins", "david", NULL),
-77821);
/* Recover original score. */
TEST_EQUAL_LOG(ngram_probv(model, "daines", "huggins", "david", NULL),
-9452);
TEST_EQUAL_LOG(ngram_probv(model, "huggins", "david", NULL), -831);
/* Un-apply weights. */
ngram_model_apply_weights(model, 1.0, 1.0, 1.0);
TEST_EQUAL_LOG(ngram_score(model, "daines", "huggins", "david", NULL),
-9452);
TEST_EQUAL_LOG(ngram_score(model, "huggins", "david", NULL), -831);
/* Recover original score. */
TEST_EQUAL_LOG(ngram_probv(model, "daines", "huggins", "david", NULL),
-9452);
/* Pre-weighting, this should give the "raw" score. */
TEST_EQUAL_LOG(ngram_score(model, "daines", "huggins", "david", NULL),
-9452);
TEST_EQUAL_LOG(ngram_score(model, "huggins", "david", NULL), -831);
/* Verify that backoff mode calculations work. */
ngram_bg_score(model,
ngram_wid(model, "huggins"),
ngram_wid(model, "david"), &n_used);
TEST_EQUAL(n_used, 2);
ngram_bg_score(model,
ngram_wid(model, "blorglehurfle"),
ngram_wid(model, "david"), &n_used);
TEST_EQUAL(n_used, 1);
ngram_bg_score(model,
ngram_wid(model, "david"),
ngram_wid(model, "david"), &n_used);
TEST_EQUAL(n_used, 1);
ngram_tg_score(model,
ngram_wid(model, "daines"),
ngram_wid(model, "huggins"),
ngram_wid(model, "david"), &n_used);
TEST_EQUAL(n_used, 3);
}
