htk_readme（htk_readme）.docVIP

htk_readme（htk_readme） Step1: gram task syntax definition file ---- (HParse) wdnet file Step2: gloable.ded (to remove the heavy note?) To generate a pronunciation dictionary dict1: HDMan -m -w.\lists\wlist -n.\lists\monophones1 -l dlog.\dict\dict1.\dict\beep.\dict\names In order to file: Names file is a proprietary name. Wlist is an ordered list of all words that appear in the task of grammar Monophones1 (generation) is used in the list of phonemes (all pronunciation phoneme to result) Dlog (Sheng Cheng) for the parameter file, put some statistics: part of the contents are as follows: Dictionary Usage Statistics --------------------------- Dictionary TotalWords WordsUsed TotalProns PronsUsed Beep 2372112325647625 NamesDict126 words required, 0 missing New Phone Usage Counts Data interchange for trade 1. K: 2 2. Ao: 4 3. L: 8 4. SP: 27 ... 26. th: 1 27. uh: 1 28. ng: 1 29. Z: 1 The dict1 is a list of all the words and the corresponding phoneme pronunciation task in the grammar. Step 3: HSGen -l -n 140 wdnet.\dict\dict1.\labels\trainprompts HSGen -l -n 15 wdnet.\dict\dict1.\labels\testprompts Trainprompts file generation testprompts is equivalent to the annotation file Example: part trainprompts: S0001 DIAL EIGHT FIVE S0002 DIAL ZERO ZERO EIGHT SIX OH ONE ZERO NINE THREE FIVE EIGHT FIVE THREE THREE NINE ZERO S0003 DIAL ZERO SIX ZERO EIGHT THREE ZERO EIGHT SEVEN SEVEN THREE FIVE ONE TWO TWO FOUR NINE SIX S0004 CALL DAVE WOOD S0005 CALL STEVE YOUNG Setp 4: Perl.\scripts\prompts2mlf.\labels\trainwords.mlf.\labels\trainprompts Perl.\scripts\prompts2mlf.\labels\testwords.mlf.\labels\testprompts Prompts2mlf is used to convert the Perl script 3 the trainprompts annotation files into a word file, each word line. For example: trainwords.mlf file: # #! MLF! S0001.lab DIAL EIGHT FIVE . S0002.lab DIAL ZERO ZERO EIGHT SIX OH ONE ZERO NINE THREE FIVE EIGHT FIVE THREE THREE NINE ZERO 处理- L - D。\，\ dict1我。\标签\ \ \ trainwords.mlf phones0.mlf mkphones0.led标签。 则把刚生成