The answering machine detection feature can be enabled on outbound calls to provide an indication of whether a call has been answered by a person or a machine. This is done by providing an amd property in a dial verb as shown in the simple example below:

{
  "verb": "dial",
  "actionHook": "/outdial",
  "callerId": "+16173331212",
  "target": [
    {
      "type": "phone",
      "number": "+15083084809",
      "trunk": "Twilio"
    }
  ],
  "amd": {
    "actionHook": "/amdEvents"
  }
}

In this example, when the dialed call is answered the answering machine detection feature will begin listening on the outbound call leg and after a short period of time will send a webhook to '/amdEvents' with an indication of whether a human or a machine has answered the call.

The payload in the webhook will look something like this:

{"type":"amd_human_detected"}

or

{"type":"amd_machine_detected","reason":"hint","hint":"call has been forwarded","language":"en-us"}

If no speech is detected at all from the far end, the payload will look like this:

{"type":"amd_no_speech_detected"}

And, finally, if the answering machine detection feature is unable to determine whether the remote party is a machine or human it will return

{"type":"amd_decision_timeout"}

The application receiving the webhook can return a new jambonz payload of verbs. For instance, say you had an outbound dialer application in which if you connect to a person you want to deliver a message, but if you connect to someone's voicemail you simply want to hang up. In that case, your app can respond to the webhook with a simple hangup verb if you receive an event payload indicating a machine has answered.

The answering machine detection feature leverages the fact that voicemail greetings are typically quite a bit more lengthy than a human's greeting. When the call is answered, speech recognition is used to determine the length of the greeting and if it is shorter than a (configurable) threshold, it is determined to be human; if longer then it is determined to be a machine.

Optionally, the feature can also given a list of common phrases that one might hear on a voicemail greeting. If any of the phrases are detected then the determination is immediately made that this is a machine. These phrases are supplied via an external file, so they can be easily updated as needed for a specific deployment. As example, here are sample phrases that might be used for an english language greeting:

{
  "en-US": [
    "call has been forwarded",
    "at the beep",
    "at the tone",
    "leave a message",
    "leave me a message",
    "not available right now",
    "not available to take your call",
    "can't take your call",
    "I will get back to you",
    "I'll get back to you",
    "we will get back to you",
    "we are unable",
    "we are not available"
  ]
}

The feature also attempts to detect audio tones, or beeps that are commonly used on voicemail systems. If detected, an event is sent via the actionHookf to the webapp.

For an application that wishes to leave a message on a voicemail system, it is necessary to know when the voicemail greeting has completed and the voicemail system is now ready to record the message. If the feature determines that the remote party is a machine, it will continue listening to the greeting until it completes and then send an event via the actionHook to the application. This can be used as a cue to let the application know that it is time to start leaving the message.

The payload that is included in the actionHook will always contain a type property describing the event type. Some event types may also include additional properties. These are described in the table below.

It is possible to receive more than one event for a single call. For instance, a possible sequence of events on a call to an answering machine is:

1. amd_machine_detected, then
2. amd_tone_detected, then
3. amd_machine_stopped_speaking

The full set of configuration parameters is shown below.

If desired, a JSON file of voicemail phrases, organized by language as shown above can be supplied. If provided, the environment variable VMD_HINTS_FILE should point to the file path to this file.

Answering machine detection can also be performed on an inbound leg by adding an amd property to a config verb. While it is less common to need to do answering machine detection on an inbound leg, this can be useful when jambonz is behind a dialer that has placed the outbound call and then connected it to jambonz by sending an INVITE to jambonz.