Modify a lexicon on a line-by-line basis. More...

Detailed Description

Modify a lexicon on a line-by-line basis.

spr_lex_cvt [-o Output lexicon](stdout) [-sent Sentence] [-bin Binary lexicon] [-c Test corpus]
    <-ci unit description files> [-cd unit description files] <-d dictionary>
    [-unwind unwind format] (-u==-ci)

Parameters

-o<em>Output	lexicon File to write the converted lexicon to (in-situ conversion is possible).
-sent<em>Sentence</em><a	name="spr_lex_cvt.sent" class="el"> 'Unwind' the given sentence and print the result.
-bin<em>Binary	lexicon Write binary lexicon to this file.
-c<em>Test	corpus Process the complete corpus instead of the dictionary. The resulting phone lattices are not (yet) written out, so this option is only usefull for timing and validation purposes.
-ci<em>unit	description files The two units description files seperated by white-space. The first file just lists the units (phones). The second file describes the context dependencies.
-cd<em>unit	description files The two units description files seperated by white-space. The first file just lists the units (phones). The second file describes the context dependencies.
-d<em>dictionary</em><a	name="spr_lex_cvt.d" class="el"> Dictionary file name.
-unwind<em>unwind	format Define the parameters to modify the word transcriptions. See spr_cwr_lex_desc_read() for more details.

Modify a lexicon on a line-by-line basis. Read a lexicon line by line, convert each word uding the given 'unwind' options (e.g. apply assimilation rules), and write out the result in an optimized format.

Author: Kris Demuynck

Date

08/08/2008 - KD: Creation.