Abstract: Methods and systems for communication interception that apply joint processing to signals and information obtained from a satellite communication network and from a cellular communication network. A processing unit processes intercepted signals from the satellite and cellular networks using shared hardware. The processing unit extracts information related to target users from communication sessions conducted by the target users in the satellite and cellular networks. The processing unit may store this information in a single data structure, and in particular correlate information pertaining to the same target user in the two networks. The processing unit may correlate the different identifiers used by the target user in the different networks, and use this correlation to enhance the tracking of this user.

Abstract: A profile or dossier of a user is constructed based partly on data culled from a data network that reveals indirect, network-mediated relationships with other individuals and groups. The profile is assembled from information, such as properties of a target individual to build an initial social circle of the target individual. References to the target individual can be derived from the direct and indirect associations in order to compile a dossier on the target individual from the references to the target individual. The initial social circle may be expanded by building respective new social circles having new associations by crawling a plurality of web sites, and deriving additional references to the target individual from the new associations in the new social circles. According to a further aspect of the method, compiling a dossier includes extracting metadata from the references.

Abstract: Methods and systems related to keyword searching processes. A list of keywords may be first represented by a set of short substrings. The substrings are selected such that an occurrence of a substring indicates a possible occurrence of one or more of the keywords. Input data may be initially pre-processed, so as to identify locations in the input data in which the substrings occur. Then, the identified locations are searched for occurrences of the actual keywords. The pre-processing scheme enables the keyword search process to search only in the identified locations of the substrings instead of over the entire input data.

Abstract: Methods and systems for identifying and tracking individuals in a area-of-interest that may be covered by a video surveillance subsystem and by a communication location subsystem, and a correlation system correlates the outputs of the two subsystems. The communication location subsystem may monitor communication of mobile phones. The video subsystem captures video images of the area-of-interest, and processes the video images so as to identify individuals who are present in the area. The correlation system correlates a given mobile phone with a given individual who was identified by the video subsystem as being engaged in a phone conversation. After correlating the mobile phone with the individual using the phone, the correlation system outputs correlated information regarding the phone and its user to an operator.

Abstract: Methods and system for predicting a future location of users of wireless communications terminals. Location information indicating respective locations of multiple wireless communication terminals may be received and processed so as to predict a future meeting among respective users of the wireless communication terminals. An action may be taken with respect to the predicted future meeting. The location information may be received from a wireless communication network to obtain a Point-of-Interest (POI) that is related to one or more of the users from a characteristic location profile of the one or more users. The POI may be indicated as the likely location of the future meeting.

Abstract: Methods and systems for finding search phrases in a body of data that is encoded using any of multiple possible character encoding schemes. An analytics system accepts an input search phrase for searching in a certain body of data. The system identifies two or more candidate character encoding schemes, which may have been used for encoding the body of data. Having determined the candidate encoding schemes, the system translates the input search phrase into multiple encoding-specific search phrases that represent the input search phrase in the respective candidate encoding schemes. The system then searches the body of data for occurrences of the input search phrase using the multiple encoding-specific search phrases.

Abstract: Systems and methods of automated adaptation of a language model for transcription of audio data include obtaining audio data. The audio data is transcribed with a language model to produce a plurality of audio file transcriptions. A quality of the plurality of audio file transcriptions is evaluated. At least one best transcription from a plurality of audio file transcriptions is selected based upon the evaluated quality. Statistics are calculated from the selected at least one best transcription from the plurality of audio file transcriptions. The language model is modified from the calculated statistics.

Abstract: A method of zoning a transcription of audio data includes separating the transcription of audio data into a plurality of utterances. A that each word in an utterances is a meaning unit boundary is calculated. The utterance is split into two new utterances at a work with a maximum calculated probability. At least one of the two new utterances that is shorter than a maximum utterance threshold is identified as a meaning unit.

Abstract: Systems and methods of script identification in audio data obtained from audio data. The audio data is segmented into a plurality of utterances. A script model representative of a script text is obtained. The plurality of utterances are decoded with the script model. A determination is made if the script text occurred in the audio data.

Abstract: Methods, systems, and computer readable media for automated transcription model adaptation includes obtaining audio data from a plurality of audio files. The audio data is transcribed to produce at least one audio file transcription which represents a plurality of transcription alternatives for each audio file. Speech analytics are applied to each audio file transcription. A best transcription is selected from the plurality of transcription alternatives for each audio file. Statistics from the selected best transcription are calculated. An adapted model is created from the calculated statistics.

Abstract: A method executed by a computer system for detecting edges comprises receiving an image comprising a plurality of pixels, determining a phase congruency value for a pixel, where the phase congruency value comprises a plurality of phase congruency components, and determining if the phase congruency value satisfies a phase congruency criteria. If the phase congruency value satisfies the phase congruency criteria, the computer system categorizes the pixel as an edge pixel. If the phase congruency value does not satisfy the phase congruency criteria, the computer system compares a first phase congruency component of the plurality of phase congruency components to a phase congruency component criteria. If the first phase congruency component satisfies the phase congruency component criteria, the computer system categorizes the pixel as an edge pixel, and if the first phase congruency component does not satisfy the phase congruency component criteria, categorizes the pixel as a non-edge pixel.

Abstract: Methods and systems for extracting speech from such packet streams. The methods and systems analyze the encoded speech in a given packet stream, and automatically identify the actual speech coding scheme that was used to produce it. These techniques may be used, for example, in interception systems where the identity of the actual speech coding scheme is sometimes unavailable or inaccessible. For instance, the identity of the actual speech coding scheme may be sent in a separate signaling stream that is not intercepted. As another example, the identity of the actual speech coding scheme may be sent in the same packet stream as the encoded speech, but in encrypted form.

Abstract: Systems and methods automatedly evaluate a transcription quality. Audio data is obtained. The audio data is segmented into a plurality of utterances with a voice activity detector operating on a computer processor. The plurality of utterances are transcribed into at least one word lattice with a large vocabulary continuous speech recognition system operating on the processor. A minimum Bayes risk decoder is applied to the at least one word lattice to create at least one confusion network. At least conformity ratio is calculated from the at least one confusion network.

Abstract: Voice activity detection (VAD) is an enabling technology for a variety of speech based applications. Herein disclosed is a robust VAD algorithm that is also language independent. Rather than classifying short segments of the audio as either “speech” or “silence”, the VAD as disclosed herein employees a soft-decision mechanism. The VAD outputs a speech-presence probability, which is based on a variety of characteristics.

Abstract: In a method of diarization of audio data, audio data is segmented into a plurality of utterances. Each utterance is represented as an utterance model representative of a plurality of feature vectors. The utterance models are clustered. A plurality of speaker models are constructed from the clustered utterance models. A hidden Markov model is constructed of the plurality of speaker models. A sequence of identified speaker models is decoded.

Abstract: People are counted in a segment of video with a video processing system that is configured with a first set of parameters. This produces a first output. Based on this first output, a second set of parameters is chosen. People are then counted in the segment of video using the second set of parameters. This produces a second output. People are counted with a video played forward. People are counted with a video played backwards. The results of these two counts are reconciled to produce a more accurate people count.

Abstract: Methods and systems for automated generation of malicious traffic signatures, for use in Intrusion Detection Systems (IDS). A rule generation system formulates IDS rules based on traffic analysis results obtained from a network investigation system. The rule generation system then automatically configures the IDS to apply the rules. An analysis process in the network investigation system comprises one or more metadata filters that are indicative of malicious traffic. An operator of the rule generation system is provided with a user interface that is capable of displaying the network traffic filtered in accordance with such filters.

Abstract: Methods and systems for analyzing network traffic. An analysis system receives network traffic, which complies with a certain protocol. The received network traffic carries a data item, which may be of value to an analyst. In order to access the data item in question, the analysis system automatically identifies the media type of the data item, by processing the network traffic irrespective of the protocol. The analysis system identifies the media type irrespective of the protocol in order to avoid the computational complexity involved in decoding the protocol.

Abstract: A method for automatically providing a plurality of additional database query terms comprising receiving a first query term from a user, receiving a plurality of characters from the user, wherein the plurality of characters is only a portion of a second query term, and selecting a set of records from a database based on the query term, wherein the database comprises records which comprise text translated from audio. The method also determines a plurality of additional query terms based on the plurality of characters, and, for at least one of the plurality of additional query terms, processes at least a portion of the set of records to determine a relevance of the additional query term. Finally, the method includes displaying at least one of the plurality of additional query terms to the user for selection based on the relevance of at least one of the plurality of additional query terms.

Abstract: A method of evaluating scripts in an interpersonal communication includes monitoring a customer service interaction. At least one portion of a script is identified. At least one script requirement is determined. A determination is made whether the at least one portion of the script meets the at least one script requirement. An alert is generated indicative of a non-compliant script.