Showing papers by "NICE Systems published in 2006"

Method and apparatus for fraud detection

Abstract: An apparatus and method for detecting a fraud or fraud attempt in a captured interaction. The method comprising a selection step in which interactions suspected as capturing fraud attempts are selected for further analysis, and assigned a first fraud probability, and a fraud detection step in which the voice is scored against one or more voice prints, of the same alleged customer or of known fraudsters. The first fraud or fraud attempt probability is combined with the result of the scoring of the fraud detection step, to generate a total fraud or fraud attempt probability. If the total fraud or fraud attempt probability exceeds a threshold, a notification is issued. The selection, scoring and combination thereof are performed using user-defined rules and thresholds.

Method and system for automatic quality evaluation

Abstract: A method and apparatus for automatic quality evaluation of an activity related to an organization, such as an agent of an organization which interacts with a calling party, a product, a campaign or the like, based on any combination of one or more of the following: the interaction itself and particularly its vocal part; meta data related to the call, to the call parties or to the environment; information extracted from the call or general information. The method may be activated off-line or on-line, in which case all alert can be generated for one or more calls.

Method and apparatus for large population speaker identification in telephone interactions

Abstract: A method and apparatus for determining whether a speaker uttering an utterance belongs to a predetermined set comprising known speakers, wherein a training utterance is available for each known speaker. The method and apparatus test whether features extracted from the tested utterance provide a score exceeding a threshold when matched against one or more of models constructed upon voice samples of each known speaker. The method and system further provide optional enhancements such as determining, using, and updating model normalization parameters, a fast scoring algorithm, summed calls handling, or quality evaluation for the tested utterance.

Apparatus and method for target oriented law enforcement interception and analysis

Abstract: An apparatus and method for capturing, processing and analyzing multiple communication items, related to a hierarchy consisting of cases, sub-cases, targets or interception criteria associated with a law enforcement organization. The apparatus and method allow a user to define the hierarchy, receive and process communication items, display the content, meta data, external or additional data related to the communication items or to a target. The apparatus comprises one or more front end units responsible for filtering and capturing communications, and one or more back end units which allow the processing and presentation of the communications.

Method and apparatus for segmentation of audio interactions

Abstract: A method and apparatus for segmenting an audio interaction, by locating anchor segment from each side of the interaction, iteratively classifying additional segments into one of the two sides, and scoring the resulting segmentation, If the score result is below a threshold, the process is repeated until the segmentation score is satisfactory or until a stopping criterion is met. The anchoring and the scoring steps comprise using additional data associated with the interaction, a speaker thereof, internal or external information related to the interaction or to a speaker thereof or the like.

Voice over IP forwarding

Abstract: A system for forwarding packed-based media in a network, the system comprising: a) at least one forwarder, configured to extract at least one packet of media from at least one media source accessible to the forwarder, and to forward the extracted packet of media to at least one capture device, and b) a forwarding manager, communicating with the forwarder, using a predefined protocol, the communicating comprising receiving media accessibility information relating to the forwarder and the at least one media source accessible to the forwarder and receiving a request identifying a media source, and configured to list at least one of the forwarders, wherein the listed forwarders are usable for forwarding the at least one packet of media from the identified media source according to the media accessibility information.

Voice over IP capturing

Abstract: An apparatus for Voice over IP capturing in a network, comprising: a data receiver, tapping the network and configured to receive at least one data packet transmitted in the network, a VoIP identifier, associated with the data receiver, configured to determine if the received data packet is a VoIP data packet qualifying for forwarding to a capture device, and a forwarder, associated with the VoIP identifier, configured to forward a copy of the qualifying VoIP data packet to at least one capture device, and to forward the received data packets back to the network.

Automatic speech analysis

Abstract: A system for providing automatic quality management regarding a level of conformity to a specific accent, including, a recording system, a statistical model database with statistical models representing speech data of different levels of conformity to a specific accent, a speech analysis system, a quality management system. Wherein the recording system is adapted to record one or more samples of a speakers speech and provide it to the speech analysis system for analysis, and wherein the speech analysis system is adapted to provide a score of the speakers speech samples to the quality management system by analyzing the recorded speech samples relative to the statistical models in the statistical model database.

How to Deal with Multiple-Targets in Speaker Identification Systems?

Abstract: In open-set speaker identification systems a known phenomenon is that the false alarm (accept) error rate increases dramatically when increasing the number of registered speakers (models). In this paper, we demonstrate this phenomenon and suggest a solution using a new model-dependent score-normalization technique, called top-norm. The top-norm method was specifically developed to improve results of open-set speaker identification systems. Also, we suggest a score-normalization parameter adaptation technique. Experiments performed using speaker recognition corpora are described and demonstrate that the new method outperforms other normalization methods

Upgrading performance using aggregated information shared between management systems

Abstract: A method of sharing information between computerized systems in an organization (100), including, collecting information from multiple computerized systems used by an organization, analyzing the collected information to derive new information based on collected information, feeding the new information to more than one of the multiple computerized systems, utilizing the new information to affect the function of the computerized system to which it was fed, wherein the collecting and the feeding is performed on more than one type of computer based management system.

Third party recording of data transferred using the IP protocol

Abstract: A method or apparatus for managing monitoring of packet data traffic of a packet switched telephony trunk connection, such as an IP trunk, wherein the data packets identify ports but monitoring is based on extension lines and the like. A mapping unit is used for obtaining mapping data that relates ports to respective individual connections or extension lines. A packet duplication unit copies data traffic from the trunk, and an associative access unit either stores or allows direct use of the data via the mapping information.

Method and Apparatus for Combining Traffic Analysis and Monitoring Center in Lawful Interception

Abstract: A method and apparatus for integrating intercepted information with information obtained from an at least one data retention source, the method comprising receiving intercepted information from an interception source, receiving information from a data retention source, and analyzing the information received from the data retention source, in association with the intercepted information. The intercepted information can comprise meta data related to the intercepted communications, and/or the contents of the communication themselves. This enables a user such as a law enforcement agency to reveal possibly indirect connections between target entities s wherein the connections involve non-target entities. The method and apparatus combine interception and content analysis methodologies with traffic analysis techniques.

Method and apparatus for lawful interception of web based messaging communication

Abstract: A method and apparatus for web based mail lawful interception. The method and apparatus enable the detection and automatic analysis of web based mail interactions out of all intercepted web pages. The method and apparatus use and possibly generate scripts for identifying a web page as comprising a web mail message, and scripts for analyzing the web mail messages.