Speaker identification identifies the gender of speakers and identifies speakers that IDOL Speech Server has been trained to recognize. This section describes the parameters that you can use to configure speaker identification.
Configuration Parameter | Description |
---|---|
AstPath | (Deprecated) The path to the speaker classifier (.ast) file for legacy speaker identification. |
ErrorMessage | The message that appears in the results when Media Server cannot connect to an IDOL Speech Server. |
Input | The audio track to process. |
MaxConsecutiveTries | The maximum number of attempts that Media Server makes to connect to the servers listed in the SpeakerIDServers parameter. |
SampleFrequency | The sample frequency of the audio to send to the IDOL Speech Server. |
SpeakerIDServers | A list of IDOL Speech Servers to use for speaker identification. |
TemplateSet | The path to the audio template set file to use for speaker identification. |
Type | The analysis engine to use. Set this parameter to SpeakerID . |
UseLegacyAction | Specifies whether to use legacy speaker identification. |
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 | TextData | The gender of the speaker. |
confidence | Int | The confidence score for speaker identification. |
|