Abstract: Disclosed is a method for training a spoken dialog service component from website data. Spoken dialog service components typically include an automatic speech recognition module, a language understanding module, a dialog management module, a language generation module and a text-to-speech module. The method includes selecting anchor texts within a website based on a term density, weighting those anchor texts based on a percent of salient words to total words, and incorporating the weighted anchor texts into a live spoken dialog interface, the weights determining a level of incorporation into the live spoken dialog interface.
Type:
Grant
Filed:
March 25, 2014
Date of Patent:
February 3, 2015
Assignee:
AT&T Intellectual Property II, L.P.
Inventors:
Srinivas Bangalore, Junlan Feng, Mazin G. Rahim
Abstract: The invention comprises computer-readable media, methods and systems for performing a dialog analysis and using that analysis to release an updated spoken dialog system. The method embodiment of the invention comprises receiving data associated with dialogs, extracting turn by turn details of the dialog and generating from the extracted details an empirical call-flow representation of the dialog. The call data may be call-logs and user audio. The empirical call-flow representation may be a finite-state machine with nodes that represent call-states and the arcs between nodes represent user responses. Nodes may also represent sub-dialogs. The call-flow representation is presented graphically to a user for easier analysis and understanding. Significant changes in the dialog can be identified as hot-spots for improvement in the next release of the spoken dialog system.
Abstract: The present invention provides a method and system for reducing the peak to average power ratio (PAP) of a signal with low computational complexity. According to one embodiment, the present invention is applied to reduce the PAP of an OFDM signal. According to an alternative embodiment, the present invention, is applied to reduce the PAP of a CDMA signal. Rather than seeking the optimum solution, which involves significant computational complexity, the present invention provides for a number of sub-optimal techniques for reducing the PAP of an OFDM signal but with much lower computational complexity.
Type:
Grant
Filed:
March 10, 2014
Date of Patent:
February 3, 2015
Assignee:
AT&T Intellectual Property II, L.P.
Inventors:
Leonard Joseph Cimini, Jr., Nelson Ray Sollenberger
Abstract: A system and a method are provided. A speech recognition processor receives unconstrained input speech and outputs a string of words. The speech recognition processor is based on a numeric language that represents a subset of a vocabulary. The subset includes a set of words identified as being for interpreting and understanding number strings. A numeric understanding processor contains classes of rules for converting the string of words into a sequence of digits. The speech recognition processor utilizes an acoustic model database. A validation database stores a set of valid sequences of digits. A string validation processor outputs validity information based on a comparison of a sequence of digits output by the numeric understanding processor with valid sequences of digits in the validation database.
Type:
Grant
Filed:
February 17, 2014
Date of Patent:
February 3, 2015
Assignee:
AT&T Intellectual Property II, L.P.
Inventors:
Mazin G. Rahim, Giuseppe Riccardi, Jeremy Huntley Wright, Bruce Melvin Buntschuh, Allen Louis Gorin
Abstract: A system and method to capture a plurality of images and store the captured images. The system has multiple camera systems capable of transmitting image data. At least one camera system is equipped with an apparatus for determining location coordinates such as GPS. A computer system monitors location coordinates, retrieves image data from the camera systems, and stores the image data into a file. A contiguous array of location coordinates is entered and the computer system locates camera systems within the contiguous array of location coordinates; retrieves image data from the located camera systems; and files the image data taken from each of the camera systems to obtain a file of image data. The system provides the ability to serially interleave frames or video captured from multiple sources.
Abstract: The burden of designing multiple training sequences for systems having multiple transmit antennas, is drastically reduced by employing a single sequence from which the necessary multiple sequences are developed. The single sequence is selected to create sequences that have an impulse-like autocorrelation function and zero cross correlations. A sequence of any desired length Nt can be realized for an arbitrary number of channel taps, L. The created sequences can be restricted to a standard constellation (that is used in transmitting information symbols) so that a common constellation mapper is used for both the information signals and the training sequence. In some applications a training sequence may be selected so that it is encoded with the same encoder that is used for encoding information symbols. Both block and trellis coding is possible in embodiments that employ this approach.
Type:
Grant
Filed:
May 11, 2010
Date of Patent:
January 27, 2015
Assignee:
AT&T Intellectual Property II, L.P.
Inventors:
Naofal Al-Dhahir, Christine Fragouli, William Turin
Abstract: A method and apparatus for routing a call based on electronic calendar entries in a communications network is described. In one embodiment, a call request to establish a connection with a subscriber of network services is received. An electronic calendar associated with the subscriber is subsequently accessed. Afterwards, the call request is routed to a phone number associated to a present agenda activity detailed in the electronic calendar.
Abstract: A wavelength tunable device for use in a wavelength division multiplexing (WDM) system comprising a display device for displaying at least one operating wavelength of the wavelength tunable device. The display device is electrically coupled to a control unit in the wavelength tunable device so as to display the tuned wavelength in real time. The wavelength tunable device may be, in exemplary embodiments, an optical transponder, wavelength division demultiplexer, or wavelength division multiplexer. In embodiments where the optical equipment has a plurality of tunable ports, the display device is adapted to display the operating wavelength of each tunable port.
Abstract: A centralized network system allows users at different remote sources to initiate a process to disable recording of different communication signals from the different remote sources. The communication signals are received from the different remote sources during conferences. A user request is also received from one of the remote sources to disable recording of one of the different communication signals. Users at multiple of the different remote sources are simultaneously authorized and enabled to begin a process to disable recording of one of the different communication signals.
Abstract: A method and system for assigning tasks can receive requested tasks, keep a requested-task queue, keep one or more worker statuses associated with respective workers, and assign the requested tasks from the requested-task queue to selected ones of the workers. In one embodiment, the requested tasks are telephone calls received by a network based contact center, and the workers are telephone agents associated with the network based contact center.
Abstract: A system and method to provide content and call attributes for a destination phone number using a click-to-dial connection includes accepting a query, retrieving links to a document, and searching through cached data using the query to identify relevant or destination number information. If no match is found, the method continues with accessing the document identified by the link for identifying relevant number information and creating a click-to-dial icon to link to the relevant numbers included in the relevant phone number information identified by the query. Next, a popup box for content relevant to the click-to-dial icon and a click feature on the popup box are created to retrieve call destination attributes for viewing by a user. Further, computer instructions create at least one communication connection between two communication devices after viewing call destination attributes.
Type:
Grant
Filed:
August 5, 2013
Date of Patent:
January 13, 2015
Assignee:
AT&T Intellectual Property II, L.P.
Inventors:
Giuseppe Di Fabbrizio, Narendra K. Gupta
Abstract: A network having distribution of access point loading includes access points to which mobile stations can associate themselves based upon access point beacon signal levels and loading levels for the various access points. A mobile station receives beacon signals from various access points and determines a signal strength for the received beacon signals. The mobile station also receives access point loading information from the access points. The mobile station associates with an access point based upon the access point beacon signal strengths and the access point loading information.
Abstract: A method and apparatus for enabling a subscriber who is originating a call to a called party endpoint to specify call handling treatments when a busy or a no answer network condition is encountered when calling the called party endpoint with no subscribed network based voice mail service are disclosed. The subscriber, for example, can re-originate the call that is originally directed to a home phone number of the called party to a cellular phone number of the called party instead upon encountering a busy or no answer network condition.
Abstract: The present invention is a system and method for failing over from a current network access medium to an alternative network access medium. A customer premises equipment (CPE) box has ports for connections to a network through several network access media, such as high speed cable connections, DSL connections and dial-up connections. QoS parameters for each of the connections are monitored from a bandwidth manager remote from the CPE box. When it is determined that a fail-over would be beneficial, a message is sent from the bandwidth manager to the CPE box containing a command to fail-over and an identity of the alternate network access media.
Type:
Grant
Filed:
March 5, 2014
Date of Patent:
January 13, 2015
Assignee:
AT&T Intellectual Property II, L.P.
Inventors:
Yihsiu Chen, Mark Jeffrey Foladare, Samuel Glazer, Shelley B. Goldman, Thaddeus Julius Kowalski
Abstract: The present invention provides a complete virtual multi-vendor EMS based network that behaves identical to the network elements of the EMS clients. A virtual network simulator is built that has the ability to faithfully simulate the behavior of any vendor's EMS to represent the data objects required by the TMF 814 specification. This allows automatic provisioning and maintenance of the Operation Support Systems to fully test new functionality against complete EMS based network without depending upon the availability of any physical equipment, thereby providing much quicker, low cost, extremely life-like testing environment.
Abstract: A method and system for monitoring data packet traffic in a multicast network comprising determining a first packet count received at a receiver router, representing a quantity of data packets associated with a multicast group and source at a first time, determining a second packet count received at that receiver router representing a quantity of data packets associated with that multicast group and source, at a second time subsequent to the first time, comparing the second packet count to the first packet count, and indicating an alarm in response to the second packet count being less than a predetermined value greater than the first packet count. A status for multiple routers can be obtained, comprising a difference between the quantity of the first and second packet counts; and indicating a warning in response to at least one of the plurality of router status being less than the predetermined value.
Abstract: The present invention is a system and method for enabling multicast synchronization of initially unicasted content. Multiple unicast streams are synchronized in order to convert the unicast streams into a multicast stream. Each unicast stream may be accelerated or slowed down in relation to a reference stream to a common point within each stream upon which the unicast streams are replaced by a multicast stream of the same content.
Abstract: In an embodiment of a messaging system, a method for presenting a commercial message to a user is provided. A target language in which the user is comfortable communicating may be determined based on at least one communication received by the user or at least one communication provided by the user. The commercial message may be presented to the user in the target language.
Abstract: A method, apparatus and machine-readable medium are provided. A phonotactic grammar is utilized to perform speech recognition on received speech and to generate a phoneme lattice. A document shortlist is generated based on using the phoneme lattice to query an index. A grammar is generated from the document shortlist. Data for each of at least one input field is identified based on the received speech and the generated grammar.
Type:
Grant
Filed:
August 26, 2005
Date of Patent:
December 30, 2014
Assignee:
AT&T Intellectual Property II, L.P.
Inventors:
Cyril Georges Luc Allauzen, Sarangarajan Parthasarathy
Abstract: A compressed rendition of a video program is provided in a format suitable for electronic searching and retrieval. An electronic pictorial transcript representation of the video program is initially received. The video program has a video component and a second information-bearing media component associated therewith. The pictorial transcript representation includes a representative frame from each segment of the video component of the video program and a portion of the second media component associated with the segment. The electronic pictorial transcript is transformed into a hypertext format to form a hypertext pictorial transcript. The hypertext pictorial transcript is subsequently recorded in an electronic medium.