Language Identification

Language identification identifies the language of speech.

Configuration Parameter Description
ClosedSet A Boolean that specifies whether the speech is expected to be in a known language, or one of the languages specified by Languages if you have set that parameter.
Input The audio track to analyze.
Languages A comma-separated list of languages that you expect to occur in the ingested media.
MaxResults Specifies how many possible languages to return in the results.
Mode The type of language identification task to run (boundary/segmented/cumulative).
OutputIdentities The types of results to include in the output (all, known, or unknown).
SampleFrequency The sample frequency to use when analyzing the audio.
SegmentDuration The amount of audio to analyze as a single segment.
SpeedBias Specifies whether to prioritize accuracy or processing speed.
Type The analysis engine to use. Set this parameter to LanguageID.

Output Tracks

The following table describes the tracks that are generated by this engine. The Output column indicates whether the information contained in the track is included by default in the output created by an output task (when you don't set the Input parameter for the output task).

Output track Description Output
Result Contains one record, describing the analysis results, for each language identification (records in this track can span multiple analyzed segments if the identified language is the same). Yes
ResultWithSource Use this track as input for a speech-to-text task. It provides both language ID results and the audio. No
SegmentedResult Media Server adds a record to this track for each analyzed segment. The records describe the results of language identification. Yes

For more information see Language Identification Results or use the action GetExampleRecord.