Answering Machine Detection
What is Answering Machine Detection?
Answering Machine Detection is a technology that allows outbound dialers to identify calls answered by answer machines and voicemails.
How does Answering Machine Detection work?
AMD works based on the following 3 algorithms.
- background noise (rumble and hiss) associated with an answering machine.
- a long string of words in one burst such as “Hello we’re not home right now, but leave a message at the beep.”
- a live person answering saying something like “hello, hello”
Why is Answering Machine Detection important?
One the main goals of answering machine detection is to start playing the recorded message at the right time.
For a live answer, it is after a person says .Hello’.
For an answering machine, it is after the sound of the beep.
Another benefit of answering machine detection is the option to play a message to the people who answer live and a different message to answering machines and voicemails.
This is especially important when doing a live transfer campaign. In a live transfer campaign, the live answer message will say something like “Press 0 to be connected to our office to schedule your appointment.”
Obviously, that would sound weird if that same live answer message was left of answering machines.
In most cases, the live answer message will be played to people who answer and the answering machine message will be played to answering machines and voicemail systems.
Is Answering Machine Detection 100% accurate?
Unfortunately, the answer is no. The problem is that Answer Machine Detection is not an exact science and causes one of two problems.
- Delay while the system tries to connect an agent. This often results in the caller saying “hello, hello” and then hanging up.
- False positives. This is where the autodialer incorrectly guesses a real person as an answering machine and hangs up the call. The effect of this is that the customer will effectively get a silent call.
With that being said, Sigma Voice is proud to say out Answering Machine Detection is greater than 95% accurate, which is very good as compared to other automated calling companies.
We are always trying to improve it as well.