Language Identification Results

The following XML shows a single record produced by language identification.

<record>
    <timestamp>
        ...
    </timestamp>
    <trackname>LanguageId.Result</trackname>
    <LanguageIdResult>
        <id>9e43e7a7-ffa8-446e-b17e-670617dbcf09</id>
        <language>FRFR</language>
        <score>0.7</score>
        <confidence>5.1</confidence>
        <rank>1</rank>
    </LanguageIdResult>
</record>

The record contains the following information:

  • id - a unique identifier for the section of audio.
  • language - the language code of the detected language. If you set the configuration parameter ClosedSet to FALSE, Media Server can decide that the language is unknown and return a result with an empty language field. For a list of language codes, see Speech Analysis Supported Languages.
  • score - the confidence score, from 0 to 1 where 1 indicates maximum confidence.
  • rank - by default, Media Server only outputs a result for the most likely language, and all result records have a rank of 1. If you set the configuration parameter MaxResults to a value greater than 1, language identification outputs other possible languages for each audio segment. The second most likely has a rank of 2, the third a rank of 3, and so on.