AudioCodes Mediant 3000 User Manual page 201

User's Manual
Note:
pattern and silence duration, the language on which the detection algorithm is based,
is in most cases not important as these factors are similar across most languages.
Therefore, the default, pre-installed AMD Sensitivity file, which is based on North
American English, may suffice your deployment even if the device is located in a
region where a language other than English is used.
The device supports up to eight AMD algorithm suites called Parameter Suites, where each
suite defines a range of detection sensitivity levels. Sensitivity levels refer to how
accurately, based on AudioCodes voice detection algorithms, the device can detect
whether a human or machine has answered the call. Each level supports a different
detection sensitivity to human and machine. For example, a specific sensitivity level may
be more sensitive to detecting human than machine. In deployments where the likelihood
of a call answered by an answering machine is low, it would be advisable to configure the
device to use a sensitivity level that is more sensitive to human than machine. Each suite
can support up to 16 sensitivity levels (0 to 15), except for Parameter Suite 0, which
supports up to 8 levels (0 to 7). The default, pre-installed AMD Sensitivity file, based on
North American English, provides the following Parameter Suites:

Parameter Suite 0 (normal sensitivity) - contains 8 sensitivity detection levels

Parameter Suite 1 (high sensitivity) - contains 16 sensitivity detection levels
As Parameter Suite 1 provides a greater range of detection sensitivity levels (i.e., higher
detection resolution), this may be the preferable suite to use in your deployment.
The Parameter Suite and sensitivity level can be applied globally for all calls, or for specific
calls using IP Profiles. For enabling AMD and selecting the Parameter Suite and sensitivity
level, see 'Configuring AMD' on page 204.
The tables below show the success rates of the default, pre-installed AMD Sensitivity file
(based on North American English) for correctly detecting "live" human voice and
answering machine:
Approximate AMD Normal Detection Sensitivity - Parameter Suite 0 (Based on North American
AMD Detection
Sensitivity
0 (Best for
Answering
Machine)
1
2
3
4
5
6
7 (Best for Live
Calls)
Version 6.8
As the main factor (algorithm) for detecting human and machine is the voice
Success Rate for Live Calls
-
82.56%
85.87%
88.57%
88.94%
90.42%
90.66%
94.72%
English)
Performance
Success Rate for Answering Machine
201
15. Media
-
97.10%
96.43%
94.76%
94.31%
91.64%
91.30%
76.14%
Mediant 3000