HTK-HDMan

HDMan:is used to prepare a pronunciation dictionary from one or more souces.It reads in a list of editing commands from a script file and then outputs an edited and merged copy of one or more dictionaries.

$ HDMan -A -D -T 1 -m -w wlist -n monophonesl -i -l dlog dict ../lexicon/voxforge_lexicon

parameter:

  -m :Merge pronunciations from all source dictionaries.By default,HDMan genergents a single pronunciation for each word. IF several input dictionaries have pronunctions for a word, then the first encountered if used.

  -w f:Load the word list stored in file f. Only prounciations for the words in this list will be extracted from the source fictionaries.

   -n f:Output a list of all distinct phones encountered to file f.
   -i : Include word output symbols in the putput dictionary.
   -l s: Write a log file to s. The log file will include dictionary statistice and a list of the number of occurrences of each phone.


一些常用命令：
AS: A B Append silence models A B, etc to each each pronunciation.
  比如：AS sp:在每一个因素后面加上sp（小停顿）
RS: Remove stress marking. Currently the only stress marking system    supported is that used in the dictionaries produced by Carnegie Melon University (system = cmu).

MP:X A B :Merge any sequence of phones A B  and rename as X
MP:sil sp sil 把sil和sp合并为sil