Answering Machine Detection (AMD)

The device's Answering Machine Detection (AMD) feature can detect if an outbound call has been answered by a human (including fax) or an answering machine. It analyzes the sound patterns (speech) received during the initial seconds of the call to determine what answered the call. Typically, when a human answers, there is a brief "hello" followed by silence, waiting for the other party's response. In contrast, when an answering machine answers the call, there is constant speech (i.e., answering message) followed by a beep, indicating the start of voicemail recording.

Once the device detects what answered the call (human or machine), it can notify, for example, a third-party application server used for automatic dialing applications. The X-Detect SIP header is used for requesting event detection and notification. For more information, see Event Detection and Notification using X-Detect Header. The device can also detect beeps at the end of an answering machine's greeting message. For more information, see Detecting Answering Machine Beeps.

Default AMD Feature

By default, the device's AMD feature is based on voice detection for North American English (see note below). It uses sophisticated speech detection algorithms that are derived from hundreds of real-life recordings of answered calls by live voices and answering machines in English. The algorithms detect whether it's human or machine, based on voice and silence duration, as well as speech patterns. The algorithms of the language-based recordings are compiled into an AMD Sensitivity file, which is pre-installed on the device.

However (despite note above), if you need to implement AMD in a different language or region, or if you wish to fine-tune the default AMD algorithms to suit your specific deployment, contact your AudioCodes sales representative for more information on this service. You may be required to provide AudioCodes with a database of recorded voices (calls) in the language on which the device's AMD feature can base its voice detector algorithms. The data needed for an accurate calibration should be recorded under the following guidelines:

■

Statistical accuracy: The number of recorded calls should be as high as possible (at least 100) and varied. The calls must be made to different people. The calls must be made in the specific location in which the device's AMD feature is to operate.

■

Real-life recording: The recordings should simulate real-life answering of a called person picking up the phone, and without the caller speaking.

■

Normal environment interferences: The environment in which the recordings are done should simulate real-life scenarios, in other words, not sterile but not too noisy either. Interferences could include, for example, background noises of other people talking, spikes, and car noises.

Once you provide AudioCodes with your database of recordings, AudioCodes compiles it into a loadable file, which can be installed on the device. For a brief description on file format and installation, see AMD Sensitivity File.

Parameter Suites and Sensitivity Levels

The device supports up to eight AMD algorithm suites, referred to as Parameter Suites. Each Parameter Suite defines a range of detection sensitivity levels for detecting whether a call is answered by a human or a machine. Sensitivity levels determine how precisely (accurately) the device distinguishes between human voices and answering machines. A lower sensitivity level favors detection of answering machines while a higher level favors detection of human. In deployments where the likelihood of a call being answered by an answering machine is low, it would be advisable to configure a high sensitivity level (which is more sensitive to human than machine). This also allows you to tweak sensitivity to comply with local regulations, such as rules designed to protect consumers when answering automated calls (for example, consumer answers and hears silence).

Each Parameter Suite supports 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) includes two Parameter Suites:

■

Parameter Suite 0 (normal sensitivity): 8 sensitivity levels

■

Parameter Suite 1 (high sensitivity): 16 sensitivity levels

Because Parameter Suite 1 provides a greater range of detection sensitivity levels (i.e., higher detection resolution), it may be more suitable for your deployment, , providing greater flexibility in tuning the sensitivity.

The detected AMD type (human or machine) and the success of correctly detecting the type are sent in CDRs and syslog messages. For more information, see Syslog Fields for Answering Machine Detection (AMD).

The Parameter Suite and sensitivity level can be applied globally for all calls using standalone parameters, or for specific calls using IP Profiles. For enabling AMD and configuring sensitivity, see Configuring AMD.

The following tables show the success rates of the default, pre-installed AMD Sensitivity file (based on North American English) for accurately detecting "live" human voices and answering machines:

Approximate AMD Normal Detection Sensitivity - Parameter Suite 0 (Based on North American English)

AMD Detection Sensitivity Level	Performance
	Success Rate for Live Calls	Success Rate for Answering Machine
0 (Best for Answering Machine)	-	-
1	82.56%	97.10%
2	85.87%	96.43%
3	88.57%	94.76%
4	88.94%	94.31%
5	90.42%	91.64%
6	90.66%	91.30%
7 (Best for Live Calls)	94.72%	76.14%

Approximate AMD High Detection Sensitivity - Parameter Suite 1 (Based on North American English)

AMD Detection Sensitivity Level	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	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%