Language identifier

A language identifier is part of the grammar header that specifies the language to be used when performing decodes.

The format of the language identifier follows the convention set out by RFC 3066. In a nutshell, the identifier is a language and country pair, like "en-US" for United States English. For more information, see Working With Languages.

The LumenVox Speech Engine currently supports the following languages:

  

Language Code

  
  

Description

  
  

en-US

  
  

American English acoustic model and dictionary

  
  

en-AU

  
  

Australian English acoustic model and dictionary

  
  

en-GB

  
  

U.K. English acoustic model and dictionary

  
  

en-IN

  
  

Indian English acoustic model and dictionary

  
  

es-MX

  
  

Mexican Spanish acoustic model and dictionary

  
  

es-CO

  
  

South American Spanish acoustic model and dictionary

  
  

fr-CA

  
  

French Canadian acoustic model and dictionary

  
  

pt-BR

  
  

Brazilian Portuguese acoustic model and dictionary

  
  

de-DE

  
  

German acoustic model and dictionary

  
  

it-IT

  
  

Italian acoustic model and dictionary

  

To specify the interaction mode in a grammar, use the following syntax in your grammar:

ABNF

 language en-US;


GrXML 

<grammar language="en-US" ... >

 

Digits-only Grammars

Prior to legacy version 9.1, LumenVox supported a non-standard language type with a suffix of "-di" to indicate the language only included digits.

This functionality is now obsolete, as the Engine will automatically determine when it should use a digits-only acoustic model. If you specify a language with a suffix of "-di" it will    be ignored by the Engine in any release starting with legacy version 9.1.


Was this article helpful?
Copyright (C) 2001-2024, Ai Software, LLC d/b/a LumenVox