AMD determines whether a human is talking to you or a robot. It does this by checking various voice parameters (Fig. 1) specific to the recording.
It consists of the following elements (Fig. 1):
Use AMD;
Transfer NOTSURE to an agent.
Fig. 1. AMD tab
AMD does not detect 100% autoresponders.
Calls will take longer to connect to an agent because the system listens for the first few seconds of the call to determine if it is an answering machine or an agent.
1.1. Use AMD
The switch is responsible for enabling and disabling AMD autodetect.
- the autodetect is enabled;
- the autodetect is disabled.
This field specifies the maximum number of words in the greeting. It is considered a robot if more than indicated words are spoken.
The minimum pause (silence) between words is indicated to determine the following word (in milliseconds).
This field specifies the maximum word length in milliseconds.
Specifies the minimum duration of a continuous voice sound in milliseconds.
Specifies the maximum time allowed to recognize if it is a human in milliseconds.
Specifies the maximum duration of silence between words in milliseconds.
This specifies the duration of silence after the greeting in milliseconds. If the specified value is exceeded, then consider a human.
This specifies the maximum length of the greeting in milliseconds. If exceeded, then consider a robot.
Specifies the maximum duration of silence before the greeting in milliseconds. If exceeded, it is considered a robot.
1.11. Transfer NOTSURE to an agent
The switch is responsible for redirecting to an agent of the member that the auto detector could not recognize, according to the position of the switch:
Add Comment