Extensible MultiModal Annotation markup language

from Wikipedia, the free encyclopedia

Extensible MultiModal Annotation markup language ( EMMA ) is an XML- based language standard from media informatics that was created by the World Wide Web Consortium and is still being worked on. It should make it possible to display multimodal and already interpreted user inputs in a standardized way for further processing. EMMA is intended for use in so-called Multimodal Interaction Frameworks (MMI).

The following recognition systems ( Recognizers ) should (be able to) generate EMMA code:

  1. Speech recognition systems
  2. Handwriting recognition systems
  3. Media interpreter for input devices (e.g. pointing devices, keyboards)
  4. the multimodal integration component

An EMMA document provides interpretations of user inputs from the various recognition systems. It is also possible to save several interpretations of the same input with different confidence factors. Interpretation data are always described in relation to the application.

example

An application with a telephone voice recognition system, which is supposed to provide customers of a travel company with information about flight connections, generates audio data that is first interpreted. A customer would like to have all flights from Boston to Denver on March 11, 2003 announced. To do this, the application asks him to enter the place of departure, the destination and the date. The interpreter that evaluates the speech recognition input could generate the following EMMA document: 

<emma:emma version="1.0"
   xmlns:emma="http://www.w3.org/2003/04/emma"
   xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
   xsi:schemaLocation="http://www.w3.org/2003/04/emma
   http://www.w3.org/TR/emma/emma10.xsd"
   xmlns="http://www.example.com/example">
 <emma:info>
   <caller_id>
     <phone_number>2121234567</phone_number>
     <state>NY</state>
   </caller_id>
   <customer_type>residential</customer_type>
   <service_name>acme_travel_service</service_name>
 </emma:info>
 <emma:one-of id="r1" emma:start="1087995961542"
     emma:end="1087995963542">
   <emma:interpretation id="int1" emma:confidence="0.75">
     <origin>Boston</origin>
     <destination>Denver</destination>
     <date>03112003</date>
   </emma:interpretation>
   <emma:interpretation id="int2" emma:confidence="0.68">
     <origin>Austin</origin>
     <destination>Denver</destination>
     <date>03112003</date>
   </emma:interpretation>
 </emma:one-of>
</emma:emma>

The interpreter has provided two possible interpretations: The entry of the place of departure could be "Boston", but it is also possible that it is "Austin", which is less likely due to the lower value of the attribute "emma: confidence".

Web links