System and method for communication terminal surveillance based on speaker recognition
AssigneeVerint Systems Ltd.
InventorsEithan Goldfarb, Yoav Ariav
Life of this patent
Estimating the term…
Abstract
A Candidate Isolation System (CIS) detects subscribers of phone call services as candidates to be surveillance targets. A Voice Matching System (VMS) then decides whether or not a given candidate Communication Terminals (CTs) should be tracked by determining, using speaker recognition techniques, whether the subscriber operating the candidate CT is a known target subscriber. The CIS receives from the network call event data that relate to CTs in the network. The CIS detects candidate CTs using a unique candidate isolation process, which applies predefined selection criteria to the received call events data.
Claims14
Apparatus, comprising:
- a storage unit, which is configured to store targeted data comprising predetermined voiceprints of one or more target subscribers of a communication network, wherein each target subscriber communicates over the communication network using cellular communication terminals, and wherein the communication network comprises a wireless cellular network;
- and
- at least one processor, which is configured:
- to receive from the wireless cellular network, through an interface connected to the wireless cellular network, network event data pertaining to a plurality of cellular communication terminals of the communication network;
- to identify a cellular communication terminal from the plurality of cellular communication terminals of the communication network as a candidate for surveillance by processing the received data to detect some predefined selection criteria within the received data,
- to request and receive from the wireless cellular network, voice originating only from the cellular communication terminal identified as the candidate communication terminal,
- to match the voice from the candidate communication terminal to one or more target subscribers using the stored predetermined voiceprints, and
- upon finding the match, to generate match information that indicates that the voice from the candidate communication terminal is likely to have originated from the one or more target subscribers and to output the match information to a surveillance center.
A method, comprising:
- storing targeted data in a storage unit, wherein the stored targeted data comprises predetermined voiceprints of one or more target subscribers of a communication network, wherein each target subscriber communicates over the communication network using communication terminals, and wherein the communication network comprises a wireless cellular network;
- receiving from the wireless cellular network, through an interface connected to the wireless cellular network, network event data pertaining to a plurality of cellular communication terminals of the communication network;
- identifying a cellular communication terminal from the plurality of cellular communication terminals of the communication network as a candidate for surveillance by processing the received data to detect some predefined selection criteria within the received data;
- requesting and receiving from the wireless cellular network, voice originating only from the cellular communication terminal identified as the candidate candidate communication terminal;
- matching the voice from the candidate communication terminal to one or more target subscribers using the stored predetermined voiceprints;
- and
- upon finding the match, generating match information that indicates that the voice from the candidate communication terminal is likely to have originated from the one or more target subscribers and outputting the match information to a surveillance center.
Dependencies are inferred from the claim text.