Use the following procedures to run an AudioSecurity
task and retrieve the results.
To run an AudioSecurity task
Send an AddTask
action to HPE IDOL Speech Server, and set the following parameters:
Type
|
The task type. Set to AudioSecurity . |
File
|
The audio file to process. To restrict processing to a section of the audio file, set the start and end times in the |
Out
|
The file to write the results to. |
To check against a database of alarm templates to identify an alarm, also set the following parameters:
TemplateList
|
The list that specifies the names of the alarm template files. |
TemplatePath
|
The path to the directory that contains the alarm templates specified in the template list file. |
For example:
http://localhost:13000/action=AddTask&Type=AudioSecurity&File=C:/speechserver/data/Sample.wav
&TemplateList=ListManager/alarms&TemplatePath=C:/speechserver/alarmTemplates&Out=SampleSec.ctm
This action uses port 13000
to instruct HPE IDOL Speech Server, which is located on the local machine, to search the Sample.wav
file for security-related sounds and check any detected alarms against the templates in the alarms
list. The action instructs the server to write the results to the SampleSec.ctm
file.
This action returns a token. You can use the token to:
You can also set some additional optional parameters for this action. For information about the parameters for the AudioSecurity
task, see the HPE IDOL Speech Server Reference.
HPE IDOL Speech Server returns the results in the following format.
1
|
A
|
13.470
|
0.780
|
<gunshot>
|
15.515
|
1
|
A
|
19.760
|
0.860
|
<gunshot>
|
11.574
|
1
|
A
|
29.000
|
1.000
|
<UNKNOWN-ALARM>
|
0.125
|
1
|
A
|
30.000
|
1.000
|
<UNKNOWN-ALARM>
|
0.336
|
1
|
A
|
31.000
|
1.000
|
alarm_11
|
1.000
|
1
|
A
|
32.000
|
1.000
|
alarm_11
|
1.000
|
1
|
A
|
33.000
|
1.000
|
alarm_11
|
1.000
|
1
|
A
|
34.000
|
1.000
|
alarm_43
|
0.600
|
1
|
A
|
41.000
|
1.000
|
<UNKNOWN-ALARM>
|
0.256
|
1
|
A
|
42.000
|
1.000
|
<UNKNOWN-ALARM>
|
0.317
|
1
|
A
|
43.000
|
1.000
|
alarm_28
|
1.000
|
1
|
A
|
44.000
|
1.000
|
alarm_28
|
1.000
|
1
|
A
|
51.380
|
0.910
|
<gunshot>
|
11.107
|
1
|
A
|
60.000
|
1.000
|
<UNKNOWN-ALARM>
|
0.209
|
1
|
A
|
61.000
|
1.000
|
<UNKNOWN-ALARM>
|
0.261
|
1
|
A
|
62.000
|
1.000
|
alarm_25
|
1.000
|
1
|
A
|
63.000
|
1.000
|
alarm_25
|
1.000
|
1
|
A
|
64.000
|
1.000
|
alarm_11
|
1.000
|
1
|
A
|
65.000
|
0.000
|
<s>
|
1.000
|
From left to right, the columns in this file contain:
1
.A
.Note: For some security events, HPE IDOL Speech Server represents the audio as a series of one-second periods and indicates the periods within which the event is present. In these cases, the results represent the beginning of each one-second period in which the event was present, rather than the precise start and end times of the events themselves.
|