Version 6.6 173 Mediant 2000
User's Manual 13. Media
Approximate AMD Detection High Sensitivity (Based on North American English)
AMD Detection
Sensitivity
Performance
Success Rate for Live Calls Success Rate for Answering Machine
0 (Best for
Answering
Machine)
72% 97%
1
77% 96%
2
79% 95%
3
80% 95%
4
84% 94%
5
86% 93%
6
87% 92%
7
88% 91%
8 (default)
90% 89%
9
90% 88%
10
91% 87%
11
94% 78%
12
94% 73%
13
95% 65%
14
96% 62%
15 (Best for Live
Calls)
97% 46%
Note:
The device's AMD feature is based on voice detection for North American
English. If you want to implement AMD in a different language or region, you must
provide AudioCodes with a database of recorded voices in the language on which the
device's AMD mechanism can base its voice detector algorithms for detecting these
voices. The data needed for an accurate calibration should be recorded under the
following guidelines:
• Statistical accuracy: The number of recordings should be large (i.e., about 100)
and varied. The calls must be made to different people, at different times. The
calls must be made in the specific location in which the device's AMD mechanism
is to operate.
• Real-life recording: The recordings should simulate real-life answering of a person
picking up the phone without the caller speaking (until the AMD decision).
• Normal environment interferences: The environment should almost simulate real-
life scenarios, i.e., not sterile but not too noisy either. Interferences, for example,
could include background noises of other people talking, spikes, and car noises.
The SIP call flows below show an example of implementing the device's AMD feature. This
scenario example allows a third-party Application server to play a recorded voice message
to an answering machine.
To Next Page
Loading...
Need help?
General
