Speaker identification identifies the gender of speakers and identifies speakers that Media Server has been trained to recognize.
Configuration Parameter | Description |
---|---|
ClosedSet | Specifies whether the audio contains only known speakers. |
Database | The speaker database to use to recognize speakers. |
Identifier | A comma-separated list of identifiers that specifies the speakers to match against. |
Input | The audio track to process. |
OutputIdentities | The types of identities to include in the output (all , speakers , known , or unknown ). |
SampleFrequency | The sample frequency of the audio to send to the audio service. |
SyncDatabase | Specifies whether to synchronize with the training database before beginning the analysis task. |
Type | The analysis engine to use. Set this parameter to SpeakerID . |
Output track | Type | Description |
---|---|---|
Result | SpeakerIdResult | Contains a record for each section of audio spoken by a different speaker. |
Field name | Type | Description |
---|---|---|
id | UUID | A universally unique identifier to identify the section of audio described by the record. |
speakerName | TextData | The name of the speaker. |
gender | String | The gender of the speaker. |
confidence | Int | The confidence score for speaker identification. |
|