The SpkIdDevelWav
task is deprecated in HPE IDOL Speech Server version 11.4 and later. Use the IvSpkIdDevelWav task instead.
This task is still available for existing implementations, but it might be incompatible with new functionality. The task might be deleted in future.
The SpkIdDevelWav
task takes a single audio file, along with the name of the speaker the file is associated with, and generates score statistics for one or more speaker templates. These statistics are then stored in an audio template development file (.atd
).
You can use one or more development files when estimating the threshold for each speaker template. If for any audio segment the top-scoring template falls below the threshold associated with that speaker, the segment is assumed to be an unknown speaker.
For more information on development score files, see the HPE IDOL Speech Server Administration Guide.
Parameter | Description | Required |
---|---|---|
Type | The task name. Set to SpkIdDevelWav . |
Yes |
Append | Whether to append speaker scores for each audio file to a common .atd file. |
|
CompSelect | The number of template components to use for scoring. | |
DataLabel | The name of the speaker that the audio is associated with. | Yes |
DevFile | The name of the audio template development file. | Yes |
DiagFile | The name of the file to write diagnostic information to. | |
DiagLevel | The level of detail to include in the diagnostic information. | |
File | The audio file that contains the speaker example speech. | Yes |
FrameNorm | The frame normalization to use. | |
LabExt | The file extension to use for label files. | Yes, if your files have an extension other than the default (.lab )
|
LabFile | A single label file to use. | |
LabPath | The path to the label files. | Yes, if you have enabled labeling and are specifying a list of multiple files to use |
LabType | The type of labels to use. | |
MinLen | The minimum length of an audio segment. | |
Sfreq | The sample frequency of the audio file to process. | |
SugdInputChannels | The channel layout of the input media file. | |
SugdInputFrequency | The sampling rate of the input media file. | |
TemplateExt | The file extension to use for template files. | |
TemplateFile | A single speaker template file to use to generate scores. | Yes, if TemplateList is not set |
TemplateList | A list file that lists the speaker template files to use to generate scores. | Yes, if TemplateFile is not set |
TemplateName | The name associated with the template file. | Yes, if TemplateFile is set |
TemplatePath | The path to the directory that contains the template files. | Yes, if TemplateList is set and the templates are not in the default location (the SpeakerIDDir directory) |
Win | The size of each audio segment. |
http://localhost:15000/action=AddTask&Type=SpkIdDevelWav&File=C:/Data/BrownSpeech4.wav&Label=Brown&TemplateList=ListManager/speakers&DevFile=speakers.atd
This action uses port 15000 to instruct HPE IDOL Speech Server, which is located on the local machine, to generate match statistics for the speaker named Brown
by checking the example speech in BrownSpeech4.wav
against the speaker templates specified in the speakers list, and writing the results to the speakers.atd
development file.
To process streamed audio, use the SpkIdDevelStream task.
|