The GetResults
action displays the audio preprocessing results as XML in your Web browser. You can also open the .ctm file from the configured HPE IDOL Speech Server temporary directory (or another location if you specified a path in the Out
parameter).
The following is an example of results produced by the audio categorization mode.
1
|
A
|
22.800
|
1.120
|
Music/Noise
|
0.000
|
1
|
A
|
23.920
|
0.500
|
Speech
|
0.000
|
1
|
A
|
24.420
|
0.580
|
Silence
|
0.000
|
1
|
A
|
25.000
|
2.280
|
Speech
|
0.000
|
1
|
A
|
27.280
|
1.570
|
Speech
|
0.000
|
1
|
A
|
28.850
|
0.500
|
Silence
|
0.000
|
1
|
A
|
29.350
|
2.000
|
Speech
|
0.000
|
From left to right, the columns in this file contain:
1
.A
.Silence
, Music/Noise
, or Speech
.The following is an example of results produced by the clipping detection mode.
<audiopreproc> <clipping> <assessment>none</assessment> <percent_frames>0</percent_frames> </clipping> </audiopreproc>
HPE IDOL Speech Server returns both a qualitative assessment of the clipping and the percentage of affected frames.
The following is an example of results produced by the SNR calculation mode.
0.01
|
2.5
|
22
|
2.84
|
5.33
|
25
|
6.62
|
7.12
|
25
|
7.12
|
9.05
|
24
|
9.05
|
9.71
|
24
|
9.71
|
12.2
|
23
|
13.43
|
14.15
|
24
|
14.15
|
14.82
|
28
|
14.82
|
17.11
|
22
|
17.11
|
19.6
|
25
|
20.17
|
20.67
|
17
|
20.67
|
21.41
|
29
|
21.41
|
23.9
|
21
|
From left to right, the columns in this file contain:
The following is an example of results produced by the DTMF mode.
1
|
A
|
0.000
|
0.020
|
none
|
0.000
|
1
|
A
|
0.020
|
0.300
|
<DTMF-0>
|
53.942
|
1
|
A
|
0.320
|
1.040
|
none
|
0.000
|
1
|
A
|
1.360
|
0.300
|
<DTMF-1>
|
54.591
|
1
|
A
|
1.660
|
1.040
|
none
|
0.000
|
1
|
A
|
2.700
|
0.320
|
<DTMF-2>
|
52.078
|
1
|
A
|
3.020
|
1.030
|
none
|
0.000
|
1
|
A
|
4.050
|
0.320
|
<DTMF-3>
|
52.085
|
1
|
A
|
4.370
|
1.040
|
none
|
0.000
|
1
|
A
|
5.410
|
0.310
|
<DTMF-4>
|
53.31
|
From left to right, the columns in this file contain:
1
.A
.
|