You can use a set of individual speaker template files during identification by supplying a list file that specifies the templates to use. However, it might be convenient to package these templates into a single speaker set file.
Using a speaker set file has several advantages:
You can use standard HPE IDOL Speech Server tasks to add templates to an audio template set file (.ats
), remove templates from a set file, modify the threshold of a single template stored within an audio template set file, or to return information on the contents of a set file or an individual template file.
To add templates to an audio template set file
The SpkIdSetAdd
task takes one or more audio template files, and adds them to an audio template set file. If the set file already exists prior to running the task, HPE IDOL Speech Server adds the templates to the existing set.
AddTask
action to HPE IDOL Speech Server, and set the following parameters:Type
|
The task name. Set to SpkIdSetAdd . |
TemplateList
|
A list file that specifies the templates to use, along with the name associated with each template. |
TemplateSet
|
The name of the template set file. |
For example:
http://localhost:15000/action=AddTask&Type=SpkIdSetAdd&TemplateList=ListManager/speakers&TemplateSet=speakers.ats
This action uses port 15000
to instruct HPE IDOL Speech Server, which is located on the local machine, to create the speakers.ats
template set file containing the templates listed by the Listmanager/speakers
list file.
You can set additional parameters. For details of the optional parameters, see the HPE IDOL Speech Server Reference.
This action returns a token. You can use the token to:
To remove a template from an audio template set file
This task removes the named template from the audio template set. If the template named is not found within the set, a task error is given.
AddTask
action to HPE IDOL Speech Server, and set the following parameters:Type
|
The task name. Set to SpkIdSetDelete . |
TemplateName
|
The name associated with the template to remove. |
TemplateSet
|
The template set file from which to remove the template. |
For example:
http://localhost:15000/action=AddTask&Type=SpkIdSetDelete&TemplateName=Brown&TemplateSet=speakers.ats
This action uses port 15000
to instruct HPE IDOL Speech Server, which is located on the local machine, to remove the template associated with the name Brown
from the speakers.ats
template set.
You can set additional parameters. For details of the optional parameters, see the HPE IDOL Speech Server Reference.
This action returns a token. You can use the token to:
To modify the threshold of a single template in an audio template set file
You can use the SpkIdSetEditThresh
task to modify the threshold of a single template in an audio template set file.
AddTask
action to HPE IDOL Speech Server, and set the following parameters:Type
|
The task name. Set to SpkIdSetEditThresh .
|
TemplateName
|
The name of the template to modify. |
TemplateSet
|
The template set file to modify. |
Thresh
|
The value to use for the threshold. |
For example:
http://localhost:15000/action=AddTask&Type=SpkIdEditThresh&TemplateName=Brown&TemplateSet=speakers.ats&Thresh=0.5
This action uses port 15000
to instruct HPE IDOL Speech Server, which is located on the local machine, to set the threshold of the template associated with the name Brown
in the speakers.ats
template set file to 0.5
.
You can set additional parameters. For details of the optional parameters, see the HPE IDOL Speech Server Reference.
This action returns a token. You can use the token to:
To retrieve information on an audio template set file
This task produces a log file that lists the contents of the specified audio template set file.
AddTask
action to HPE IDOL Speech Server, and set the following parameters:Type
|
The task name. Set to SpkIdSetInfo . |
TemplateSet
|
The template set file to retrieve information for. |
Log
|
The log file to write the information to. |
For example:
http://localhost:15000/action=AddTask&Type=SpkIdSetInfo&TemplateSet=speakers.ats&Log=speakers.log
This action uses port 15000
to instruct HPE IDOL Speech Server, which is located on the local machine, to write information on the speakers.ats
template set file to the log file speakers.log
.
You can set additional parameters. For details of the optional parameters, see the HPE IDOL Speech Server Reference.
This action returns a token. You can use the token to:
<UBM> Yes <COMPSELECT> 8 </COMPSELECT> <FRAMENORM> UBM </FRAMENORM> <NTEMPLATES> 1 </NTEMPLATES> <TEMPLATES> <TEMPLATE_0> <NAME> Brown </NAME> <THRESH_ENABLED> Yes </THRESH_ENABLED> <THRESH_VALUE> -0.0845253 </THRESH_VALUE> <NCOMPS> 1023 </NCOMPS> <SHARE_ICOV> Yes </SHARE_ICOV> <SHARE_MEANS> Yes </SHARE_MEANS> <SHARE_MEANS_PERCENT> 71.9453 </SHARE_MEANS_PERCENT> </TEMPLATE> </TEMPLATES>
This file shows some information about how the templates were trained and optimized, along with information about each template stored in the set. The log file includes the following fields:
|
Whether a Universal Base Model is included in the set. |
|
How many components are used for each template when scoring. |
|
The method of frame score normalization used when optimizing the set. |
|
The number of templates in the set. |
|
The start of information on template 0, and so on. |
<NAME>
|
The name associated with the template. |
<THRESH_ENABLED>
|
Whether a score threshold is enabled for this template. |
<THRESH_VALUE>
|
The score threshold that has been estimated for this template. |
<NCOMPS>
|
The number of components used in this template. |
<SHARE_ICOV>
|
Whether this template shares variance statistics with a base template. |
<SHARE_MEANS>
|
Whether this template shares mean parameters with a base template. |
<SHARE_MEANS_PERCENT>
|
The percentage of mean parameter components shared with the base template. |
|