HPE IDOL Speech Server can list the 30,000 most frequent words in a specific language model.
To obtain the vocabulary listing
Send an AddTask
action to HPE IDOL Speech Server, and set the following parameters:
Type
|
The task name. Set to LmListVocab . |
Tlm
|
The language model to query. The language model file is a .tlm file in the relevant language pack. |
Out
|
The file to write the results to. |
For example:
http://localhost:13000/action=AddTask&Type=LmListVocab&Tlm=C:\LP\ENUK\ver-ENUK-5.0.tlm&Out=ENUKvocab.ctm
This action uses port 13000
to instruct HPE IDOL Speech Server, which is located on the local machine, to write the 30,000 most frequently occurring words in the ver-ENUK-5.0.tlm
language model to the ENUKvocab.ctm
file.
This action returns a token. You can use the token to:
The results specify the 30,000 most frequently occurring words, starting from the most frequent word.
In addition to listing the vocabulary, you can search the language model for a specific word and, if present, where it is ranked in terms of frequency.
To search for a word
Send an AddTask
action to HPE IDOL Speech Server, and set the following parameters:
Type
|
The task name. Set to LmLookup . |
Tlm
|
The language model to query. The language model file is a .tlm file in the relevant language pack. |
Word
|
The word to look up. |
Out
|
The file to write the results to. |
For example:
http://localhost:13000/action=AddTask&Type=LmLookup&Tlm=C:\LP\ENUK\ver-ENUK-5.0.tlm&Word=garden&Out=SearchResult.ctm
This action uses port 13000
to instruct HPE IDOL Speech Server, which is located on the local machine, to search the ver-ENUK-5.0.tlm
language model file for the word ‘garden
’ and write the results to the SearchResult.ctm
file.
This action returns a token. You can use the token to:
HPE IDOL Speech Server displays the results in the format:
Word [word], rank: xxx
where word is the search term and xxx is the frequency ranking in the language model (1
is the most frequent word).
|