Recorder Biometrics Post-Processing Audio Stream States

The Recorder Biometrics Post-Processing Audio Stream States object details the number of campaign-based audio streams in each processing state.

The object provides you with the performance counters listed in the table.

Name	Description
Post-Processing Audio Streams in Waiting State	The number of post-processing audio streams currently in the Waiting state. Audio streams remain in this state until the Biometrics Service decides whether or not it needs to process the stream.
Post-Processing Audio Streams in Streaming State	The number of post-processing audio streams currently in the Streaming state. Audio streams should quickly transition from the Streaming state to the Finishing state.
Post-Processing Audio Streams in Finishing State	The number of post-processing audio streams currently in the Finishing state. Streams typically stay in this state for most the time.
Total Post-Processing Audio Streams Wanted	The total number of post-processing audio streams that the Biometrics Service requested for full processing.
Total Post-Processing Audio Streams Not Wanted	The total number of post-processing audio streams that the Biometrics Service did need to process. Examples of when "not wanted" audio streams occur include: Insufficient CTI information to identify the parties on the interaction In Speech Analytics, an interaction represents a single part of the contact between one employee and the same customer. In Text Analytics, an interaction is the communication session between one or more employees and the same customer with a unifying contextual element.. When customer verification Feature in voice biometrics where the speaker’s voice is compared to a collection of employee or customer voiceprints that should match the call. If a match occurs, the speaker is said to be verified. or watch list List that contains one of more voiceprints of people who are of particular interest to an enterprise. detection Function of the IAFD product that compares a caller’s voice to one or more voiceprints in a watch list to detect if a target is participating in a call. is performed on a stereo interaction for only the Other Party channel, which results in the Employee channel being "not wanted."