After you have trained a set of speaker templates, use the IvSpkIdEvalStream task to run iVector-based identification of any sections of an audio stream where the trained speakers are present.
To process an audio file, use the IvSpkIdEvalWavtask.
| Parameter | Description | Required |
|---|---|---|
| Type | The task name. Set to IvSpkIdEvalStream.
|
Yes |
| AllowEmpty | Whether to produce gender labels as output if no speakers are specified. | |
| DiagFile | The name of the file to write diagnostic information to. | |
| DiagLevel | The level of detail to include in the diagnostic information. | |
| DiscardShort | Exclude segments shorter than a specific duration from further analysis. | |
| FrameDupl | The balance between performance and speed for audio preprocessing DNN classification. | |
| MaxNonSpeech | The maximum length of non-speech segments. | |
| MaxSpeech | The maximum length of speech segments. | |
| MinNonSpeech | The minimum length of non-speech segments. | |
| MinSpeech | The minimum length of speech segments. | |
| Out | The file to write the results to. | |
| Sfreq | The sample frequency of the audio stream to process. | |
| The file extension to use for template files. | ||
| TemplateList | A list file that lists multiple speaker template files to use. | |
| TemplatePath | The path to the directory containing the speaker templates. | |
| TemplateSet | An audio template set file. | |
| ThreshScale | The rate at which to scale the thresholds. |
http://localhost:15000/action=AddTask&Type=IvSpkIdEvalStream&File=C:\Data\Speech.wav&TemplateSet=speakers.ivs&Out=results.ctm
This action uses port 15000 to instruct HPE IDOL Speech Server, which is located on the local machine, to search the audio stream for speakers based on the iVector-based template set file speakers.ivs, and to write the identification results to the results.ctm file.
|
|