| AT&T CORP. Patent applications |
| Patent application number | Title | Published |
|---|
| 20120036219 | SYSTEM AND METHOD FOR EVENT DRIVEN PUBLISH-SUBSCRIBE COMMUNICATIONS - The present invention provides a system and a method for delivering an event from an event publisher to an event subscriber via an event broker. The event broker performs several functions such as receiving an event published by an event publisher of a first domain, assigning a priority based on a second domain to a plurality of subscribers of the second domain, processing the event based on a rule and the priority, and further delivering the event published by the event publisher of the first domain to the plurality of event subscribers of the second domain in accordance with the priority. | 02-09-2012 |
| 20110191580 | METHOD AND SYSTEM FOR EXECUTION MONITOR-BASED TRUSTED COMPUTING - A system and method to ensure trustworthiness of a remote service provided by a service provider. The method includes monitoring runtime dependencies invoked during execution of a service transaction associated with the remote service, the service transaction being requested by a service requester. The method further includes determining whether a deviation exists between the runtime dependencies and a trusted list of dependencies associated with the remote service. The method also includes blocking execution of the service transaction based on determining that the deviation between the runtime dependencies and the trusted list of dependencies exists. | 08-04-2011 |
| 20110179006 | SYSTEM AND METHOD FOR PROVIDING A NATURAL LANGUAGE INTERFACE TO A DATABASE - A system and method for providing a natural language interface to a database or the Internet. The method provides a response from a database to a natural language query. The method comprises receiving a user query, extracting key data from the user query, submitting the extracted key data to a data base search engine to retrieve a top n pages from the data base, processing of the top n pages through a natural language dialog engine and providing a response based on processing the top n pages. | 07-21-2011 |
| 20110175922 | METHOD FOR DEFINING ANIMATION PARAMETERS FOR AN ANIMATION DEFINITION INTERFACE - A system and a computer-readable medium are provided for controlling a computing device to define a set of computer animation parameters for an object to be animated electronically. An electronic reference model of the object to be animated is obtained. The reference model is altered to form a modified model corresponding to a first animation parameter. Physical differences between the electronic reference model and the modified model are determined and a representation of the physical differences are stored as the first animation parameter. Altering of the reference model and determining of the physical differences are repeated. The stored parameters are provided to a rendering device for generation of the animation in accordance with the stored parameters. Determining physical differences between the electronic reference model and the modified model and storing a representation of the physical differences as the first animation parameter include comparing vertex positions of the reference model. | 07-21-2011 |
| 20110173226 | SYSTEM AND METHOD OF LATTICE-BASED SEARCH FOR SPOKEN UTTERANCE RETRIEVAL - A system and method are disclosed for retrieving audio segments from a spoken document. The spoken document preferably is one having moderate word error rates such as telephone calls or teleconferences. The method comprises converting speech associated with a spoken document into a lattice representation and indexing the lattice representation of speech. These steps are performed typically off-line. Upon receiving a query from a user, the method further comprises searching the indexed lattice representation of speech and returning retrieved audio segments from the spoken document that match the user query. | 07-14-2011 |
| 20110172999 | System and Method for Building Emotional Machines - A system, method and computer-readable medium for practicing a method of emotion detection during a natural language dialog between a human and a computing device are disclosed. The method includes receiving an utterance from a user in a natural language dialog, receiving contextual information regarding the natural language dialog which is related to changes of emotion over time in the dialog, and detecting an emotion of the user based on the received contextual information. Examples of contextual information include, for example, differential statistics, joint statistics and distance statistics. | 07-14-2011 |
| 20110170543 | POINT-TO-MULTIPOINT CONNECTIONS FOR DATA DELIVERY - A method, device and non-transitory computer-readable storage medium transferring information using a network. The information transferred by connecting a destination device operatively to a storage device using the network. The storage device storing information to be transmitted to the destination device. The network providing a point-to-multipoint connection between an origin device and a plurality of destination devices. The plurality of destination devices including the destination device. Also, the information being transferred by receiving the information stored in the storage device by the destination device in response to the destination device being operatively connected to the storage device. The information received by the destination device having been transmitted from the origin device to the network prior to the destination device being operatively connected to the storage device. | 07-14-2011 |
| 20110051126 | Method for Increasing Accuracy of Measurement of Mean Polarization Mode Dispersion - A method of determining a mean square differential group delay associated with a length of optical fiber. The method including measuring a polarization mode dispersion vector as a function of frequency, using a frequency-domain polarization mode dispersion measurement apparatus. The method also including calculating a second-order polarization mode dispersion vector as a function of frequency by calculating a derivative of the polarization mode dispersion vector with respect to frequency. Also, calculating the mean of the magnitude of the second-order polarization mode dispersion vector to obtain a first result. Further, multiplying a proportionality coefficient by the first result to calculate the mean square differential group delay. | 03-03-2011 |
| 20110047185 | META-DATA INDEXING FOR XPATH LOCATION STEPS - In accordance with a method of encoding meta-data associated with tree-structured data, a first set of elements of a plurality of elements in the tree-structured is associated explicitly with explicit meta-data levels, and a second set of elements of the plurality of elements is associated by inheritance with explicit meta-data levels of closest ancestor elements of the first set of elements. The plurality of elements is packed into a plurality of leaf nodes of an index structure. The plurality of leaf nodes is merged into a plurality of non-leaf nodes until a root non-leaf node is generated. The plurality of non-leaf nodes of the index structure is associated with indicators representing ranges of the explicit meta-data levels in the packed first set of elements, such that explicit meta-data level ranges of descendant non-leaf nodes are subsets of explicit meta-data level ranges of ancestor non-leaf nodes. | 02-24-2011 |
| 20110033044 | Secure Open-Air Communication System Utilizing Multi-Channel Decoyed Transmission - A secure, open-air communication system utilizes a plurality of “decoy” data signals to hide one or more true data signals. The true data signal(s) are channel hopped with the plurality of decoy data signals to form a multi-channel “scrambled” output signal that is thereafter transmitted in an open-air communication system. The greater the number of decoy signals, the greater the security provided to the open-air system. Further security may be provided by encrypting both the true and decoy signals prior to scrambling and/or by utilizing a spatially diverse set of transmitters and receivers. Without the knowledge of the channel assignment(s) for the true signal(s), an eavesdropper may be able to intercept (and, with time, perhaps descramble) the open-air transmitted signals, will not be able to distinguish the true data from the decoys without also knowing the channel assignment(s). | 02-10-2011 |
| 20110002249 | Method for Packet-Switching Interface for Code Division Switching in a Terrestrial Wireless System - An access radio port is provided that includes means for spreading a payload data signal, extracted from an ATM packet, with a uniquely assigned orthogonal code, means for transmitting the spread payload data signal to one of a group of mobile subscriber terminals located within a microport cell of a wireless terrestrial network, and means for releasing the uniquely assigned orthogonal code. In another aspect, a mobile subscriber terminal, configured to be located within a microport cell of a terrestrial wireless network that interfaces with an access radio port, is provided. The mobile subscriber terminal includes means for receiving an assignment of a unique orthogonal code, means for spreading a payload data signal by the unique orthogonal code, means for modulating and forwarding the spread payload data signal to the access radio port, and means for releasing the assignment of the unique orthogonal code. | 01-06-2011 |
| 20100262683 | Network Aware Forward Caching - An Internet service provider includes a cache server and a network aware server. The network aware server is operable to determine an optimization between a cost of retrieving content from a network and a cost of caching content from the network at the first cache server and then send a content identifier to the cache server. The cache server is operable to receive the content identifier, and determine the source of a content item. If the source is the same as the content identifier, then the cache server caches the content item. | 10-14-2010 |
| 20100239076 | Providing Called Number Characteristics to Click-to-Dial Customers - 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. | 09-23-2010 |
| 20100226277 | METHOD AND SYSTEM OF MONITORING THE RECEIPT OF MULTICAST TRAFFIC - 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. | 09-09-2010 |
| 20100214920 | Systems and Methods for Capacity Planning Using Classified Traffic - A method of capacity planning in a network includes assigning a class of service to each packet of data on the network. Each class of service is also assigned a grade of service for different network conditions. A class bandwidth is calculated for each class of service under each network condition by multiplying an expected load for each class of service by the associated grade of service under each of the network conditions. A network condition bandwidth is calculated for each network condition by adding together the class bandwidths for all classes. A network capacity is predicted based upon the largest network condition bandwidth. A network management apparatus can perform the method. | 08-26-2010 |
| 20100208744 | System and method for compressing internet protocol rounting tables - A networking device connects to a router and to an autonomous system (AS). The networking device receives a routing table from the router, exchanges routing information with the AS, updates the routing table in response to exchanging information with the AS, coalesces the updated routing table into a compressed routing table, and sends the compressed routing table back to the router. The compressed routing table causes the router to forward data in a manner that is identical to the received routing table. | 08-19-2010 |
| 20100197286 | System and Method for Improving Cellular Telephone User Experience - A method for determining an amount of time required to download a data file to a wireless device includes receiving information indicating a first amount of wireless bandwidth allocated for the download of the data file, calculating a first length of time required to download the data file to the wireless device based on the first amount of wireless bandwidth allocated, and comparing the first length of time required to a predetermined amount of time. If the first length of time required is less than the predetermined amount of time, the download begins. If the first length of time required is more than the predetermined amount of time, information indicating the first length of time required is sent to the wireless device, a start download signal is received from the wireless device, and download of the data file to the wireless device begins in response to the start download signal. | 08-05-2010 |
| 20100169076 | Text-to-Scene Conversion - The invention relates to a method of converting a set of words into a three-dimensional scene description, which may then be rendered into three-dimensional images. The invention may generate arbitrary scenes in response to a substantially unlimited range of input words. Scenes may be generated by combining objects, poses, facial expressions, environments, etc., so that they represent the input set of words. Poses may have generic elements so that referenced objects may be replaced by those mentioned in the input set of words. Likewise, a character may be dressed according to its role in the set of words. Various constraints for object positioning may be declared. The environment, including but not limited to place, time of day, and time of year, may be inferred from the input set of words. | 07-01-2010 |
| 20100166157 | System and Method for Indexing Voice Mail Messages By Speaker - The invention provides a system and method for indexing and organizing voice mail message by the speaker of the message. One or more speaker models are created from voice mail messages received. As additional messages are left, each of the new messages are compared with existing speaker models to determine the identity of the callers of each of the new messages. The voice mail messages are organized within a user's mailbox by caller. Unknown callers may be identified and tagged by the user and then used to create new speaker models and/or update existing speaker models. | 07-01-2010 |
| 20100161799 | System and Method for Obtaining Content from a Content Delivery Network - A method receives from a first server a first domain name system (DNS) request including a first internet protocol (IP) address of the first server, and a second IP address received by the first server from a first system. The method also maps a correlation between the first IP address and the second IP address, and receives from the first server a second DNS request. In response to receiving the second DNS request, the method responds to the first server with a third IP address of a second server, wherein the third IP address is chosen based upon the second IP address. | 06-24-2010 |
| 20100161760 | Systems and Methods for Determining the Location of a Request on a Content Delivery Network - A client computing system includes a processor that receives a domain name and determines if the domain name is in a list of domain names that are associated with a content delivery network (CDN). In response to determining that the first domain name is in the list, the processor directs a domain name system (DNS) request to a CDN DNS server, instead of to the default DNS server. | 06-24-2010 |
| 20100159931 | System and Method for Inferring Wireless Trajectories in a Cellular Telephone Network - A device includes a processor configured to determine a number of users in each of a plurality of wireless telephone cells of a trajectory in a wireless telephone network. The processor is also configured to determine handoff data between each adjacent pair of the wireless telephone cells, and to determine a first number of users traveling along the trajectory in the wireless telephone network while on a telephone call. The processor also calculates a total number of users associated with the trajectory in the wireless telephone network based on the handoff data between each adjacent pair of the wireless telephone cells, and based on the first number of users traveling along the trajectory while on the telephone call. | 06-24-2010 |
| 20100158397 | Method and System for Classifying Image Elements - A method, system, and machine-readable medium for classifying an image element as one of a plurality of categories, including assigning the image element based on a ratio between an unoccluded perimeter of the image element and an occluded perimeter of the image element and coding the image element according to a coding scheme associated with the category to which the image element is classified. Exemplary applications include image compression, where categories include image foreground and background layers. | 06-24-2010 |
| 20100153802 | System and Method for Anycast Transport Optimization - A system includes first, second, and third content servers, and an edge server. The first, second, and third content servers each are configured to cache content. The edge server is in communication with the first, second, and third content servers. The edge server is configured to receive a content request, and to request different portions of the content from each of the first, second, and third content servers based on a network cost of each of the first, second, and third content servers. | 06-17-2010 |
| 20100151850 | System and Method for Adapting Mobile Applications - A method for modifying an application of a wireless device based on triggers received at the wireless device includes analyzing a network trigger and at least one other trigger associated with a wireless device, and adjusting a device-level component parameter of the wireless device based on one of the triggers. The method also synchronizes an application parameter of the wireless device with the device-level component parameter; and synchronizes the application parameter with network. A device for performing the method is also disclosed. | 06-17-2010 |
| 20100150160 | INTERWORKING OAM BETWEEN ETHERNET AND ATM/FRAME RELAY NETWORKS - The present invention provides a network system that interworks OA&M (Operations, Administration and Maintenance) failure notification data from the ATM Domain to the Ethernet Domain and vice versa. Failure indications or notifications are typically routed from one domain to another within 1-2 seconds; providing service providers and customers the ability to react quickly to network faults. This enhances the overall quality of the Ethernet-to-ATM Interworking service and provides a similar level of reliability across the Ethernet/ATM/FR domains. | 06-17-2010 |
| 20100150018 | System and Method for Testing User Connections in an Internet Protocol Television System - A method for providing a cable service dispatch ticket is disclosed. A new user installation request is received at a server in an Internet Protocol television system. An upstream data rate test is performed for each of a plurality of user connections in the Internet Protocol television system in response to the new user installation request. An upstream data rate that is determined for each of the user connections during the upstream data rate test is recorded. A cable service dispatch ticket for each of the plurality of user connections is provided when a number of the upstream data rates are below a threshold upstream data rate. A device that implements the method is also disclosed. | 06-17-2010 |
| 20100146565 | System and Method for Verifying Deployment of an Internet Protocol Television Video on Demand Asset - A system includes a subscriber event transmission interface and an enterprise data warehouse. The subscriber event transmission interface is configured to collect first video-on-demand asset metadata from a first video head-end office. The enterprise data warehouse is in communication with the subscriber event transmission interface. The enterprise data warehouse is configured to store a list of a video-on-demand assets deployed to the video head-end office based on the first video-on-demand asset metadata. | 06-10-2010 |
| 20100146143 | System and Method for Analyzing Data Traffic - A method of analyzing data traffic includes receiving a request at a data analysis system to store a string related to header information associated with a data packet. The method also includes applying a hash function to the string, thereby obtaining a 32-bit intermediate, and applying another hash function to the 32-bit intermediate, thereby obtaining a hash number. Further, the method includes storing the string in an array position corresponding to the hash number, when the array position is empty. | 06-10-2010 |
| 20100146100 | Flexible Application Classification - A system includes an information storage module and an inspection module. The information storage module is configured to store a plurality of tags. Each tag is associated with a known set of traffic types of a plurality of known sets of traffic types. The inspection module is configured to compare a traffic flow to a set of traffic types to determine a matching set of traffic types, request a tag from the information storage module, and mark the traffic flow with the tag. The tag corresponds to the matching set of traffic types. | 06-10-2010 |
| 20100146076 | Redirection of Multimedia Content Between Receiver Devices Associated with a User - A provider network is configured to redirect multimedia content between receiver devices associated with a user. Initially, a multimedia stream representative of the multimedia content is transmitted via the provider network to a first receiver device associated with the user. In response to a redirect stimulus, the provider network redirects the streaming of the multimedia content to a second receiver device associated with the user. The multimedia stream transmitted to the second receiver device can be formatted based on the characteristics of the network link between the provider network and the second receiver device, based on specified formatting rules associated with the second receiver device, and the like. The redirect stimulus can include a user-initiated redirect command provided to the provider network via the first receiver device, the second receiver device, or a third device. Alternately, the redirect stimulus can include an automated stimulus generated based on redirect rules. | 06-10-2010 |
| 20100146040 | System and Method for Content Validation - A method of obtaining content includes receiving a playfile. The playfile includes a chunk ID corresponding to a chunk of the content, a packet ID corresponding to a packet of the chunk, and a hash of the packet. The method further includes obtaining the chunk from a peer, determining a calculated hash for the packet, and discarding the chunk when the calculated hash does not match the hash in the playfile. | 06-10-2010 |
| 20100146038 | System and Method for Assigning Requests in a Content Distribution Network - A system includes a plurality of edge routers and a route controller. The edge routers are configured to direct requests from a client system to one of a plurality of cache servers. Each of the cache servers is configured to provide content to the client system in response to the requests. The route controller is configured to receive demand information from the edge routers, estimate an optimal request distribution based on the demand information using a bicriteria approximation algorithm, and provide each of the edge routers with route information. | 06-10-2010 |
| 20100138676 | Microprocessors with improved power efficiency - A microprocessor is arranged to process instructions at least some of which contain at least one immediate value which forms an operand of the function, wherein said immediate value is represented in a format which achieves a greater power efficiency than two's complement when said instructions are processed. | 06-03-2010 |
| 20100138555 | System and Method to Guide Active Participation in Peer-to-Peer Systems with Passive Monitoring Environment - A method includes identifying shared content by inspecting a peer-to-peer traffic flow and identifying source peers providing the shared content, and requesting the shared content from the source peers. The method further includes receiving requests for the shared content from requesting peers, identifying requesting peers based on the requests for the shared content, and providing the shared content to a local subset of the requesting peers. | 06-03-2010 |
| 20100134788 | Method for Increasing Accuracy of Measurement of Mean Polarization Mode Dispersion - The present invention provides a method of determining a mean differential group delay associated with a length of optical fiber. The method including measuring a magnitude of a polarization mode dispersion vector as a function of frequency, using a frequency-domain polarization mode dispersion measurement apparatus, where the magnitude of the polarization mode dispersion vector is a scalar differential group delay. Also the method calculates a frequency derivative of the scalar differential group delay from the magnitude of the polarization mode dispersion vector to obtain a first result. The frequency derivative of the scalar differential group delay being a scalar second-order polarization mode dispersion function. The method further multiplies a proportionality coefficient B | 06-03-2010 |
| 20100128918 | Method and System for Content Distribution Network Performance and Quality Measurement - A content delivery system includes an upload module, a content delivery module, and a quality assurance module. The upload module is configured to receive content from a content provider, and generate an upload signature for the content as received from the content provider. The content delivery module is configured to receive a request for the content from a client system, and provide the content to the client system. The quality assurance module is configured to generate a download signature for the content as delivered to the client, and compare the upload signature and the download signature. When the upload signature and the download signature do not match, the quality assurance module is further configured to generate an alert. | 05-27-2010 |
| 20100125800 | System and Method for Bridging Communication Services Between Virtual Worlds and the Real World - A system includes a gateway operative to couple the system to a user. The system further includes a first infolet coupled to the gateway, and operative to couple the system to a first virtual world application, a second infolet coupled to the gateway and to the first infolet, and operative to couple the system to a real world application. The system is operable to obtain first information requested by the user from the second infolet and send the first information to the virtual world application through the first infolet. | 05-20-2010 |
| 20100125643 | Interdomain Network Aware Peer-to-Peer Protocol - A method includes receiving network distance information, receiving a request from a client for an identity of a peer providing content, and identifying a first peer and a second peer providing the content. The network distance information includes a compilation of network distance information provided by a plurality of service providers. The method further includes determining that a network distance between the first peer and the client is less than a network distance between the second peer and the client based on the network distance information, and providing the identity of the first peer to the client. | 05-20-2010 |
| 20100125626 | Systems and Methods for Directing Content Requests to Servers - A method of delivering content to a client includes receiving a request for the content from the client at a first server, determining the size of the content, and determining an optimal server to provide the content. The method further includes redirecting the client to the optimal server when the size of the content is above a threshold. | 05-20-2010 |
| 20100122335 | System and Method for Filtering Unwanted Internet Protocol Traffic Based on Blacklists - A system and method for filtering unwanted Internet Protocol traffic based on blacklists receives a first blacklist containing a first plurality of Internet protocol addresses associated with unwanted Internet traffic. The system also operates a first plurality of access control lists adapted to block the unwanted Internet traffic from one of the first Internet protocol addresses listed in the first blacklist. The system also assigns a first weight to each of the first Internet protocol addresses based on a reliability of Internet traffic from each of the first Internet protocol addresses. Additionally, the system reduces a first number of the first access control lists to optimally trade off a number of desirable Internet protocol addresses blocked with a number of bad Internet protocol addresses blocked based on the first weight of each of the first Internet protocol addresses. | 05-13-2010 |
| 20100121945 | Hybrid Unicast/Anycast Content Distribution Network System - A method includes receiving a request for an edge cache address, and comparing a requester address to an anycast group. The method can further include providing an anycast edge cache address when the requestor address is in the anycast group. Alternatively, the method can further include determining an optimal cache server, and providing a unicast address of the optimal cache server when the requester address is not in the anycast group. | 05-13-2010 |
| 20100121940 | System and Method for Selectively Caching Hot Content in a Content Delivery System - A method includes receiving a request for content from a client, and determining an elapsed time since a previous request for the content. Additionally, the method includes retrieving the content from a content server and storing the content in a cache when the elapsed time since the previous request for the content is not greater than a threshold. Further, the method includes providing the content to the client. The method also includes determining a cache-hit ratio and altering a threshold in response to the cache-hit ratio. | 05-13-2010 |
| 20100114786 | WORKLIST INTEGRATION OF LOGICAL AND PHYSICAL TASKS - In accordance with a method of managing work flow, tasks associated with a telecommunications service order from a plurality of worklists of computing source systems are merged into a merged worklist. Each computing source system maintains a respective worklist that includes a task associated with the service order. The tasks of the service order in the merged worklist are prioritized into a prioritized sequence to be completed on a work-when-ready basis. An error in completion of a task associated with a worklist of a source system is detected and a new task to correct the detected error is generated. Further, the worklist of the source system associated with the detected error is updated with the new task and the new task is integrated into a proper position of the prioritized sequence in the merged worklist in accordance with the work-when-ready basis. | 05-06-2010 |
| 20100106722 | Synthetic Audiovisual Description Scheme, Method and System for MPEG-7 - A method and system for description of synthetic audiovisual content makes it easier for humans, software components or devices to identify, manage, categorize, search, browse and retrieve such content. For instance, a user may wish to search for specific synthetic audiovisual objects in digital libraries, Internet web sites or broadcast media; such a search is enabled by the invention. Key characteristics of synthetic audiovisual content itself such as the underlying 2d or 3d models and parameters for animation of these models are used to describe it. More precisely, to represent features of synthetic audiovisual content, depending on the description scheme to be used, a number of descriptors are selected and assigned values. The description scheme instantiated with descriptor values is used to generate the description, which is then stored for actual use during query/search. Typically, a user, to search for a needed synthetic audiovisual content initiates a query that is passed on to a search engine that then retrieves the candidate content from one or more databases whose description closely matches the query criteria specified by the user. | 04-29-2010 |
| 20100106491 | Voice Activity Detection and Silence Suppression in a Packet Network - The present invention is a system and method that improves upon voice activity detection by packetizing actual noise signals, typically background noise. In accordance with the present invention an access network receives an input voice signal (including noise) and converts the input voice signal into a packetized voice signal. The packetized voice signal is transmitted via a network to an egress network. The egress network receives the packetized voice signal, converts the packetized voice signal into an output voice signal, and outputs the output voice signal. The egress network also extracts and stores noise packets from the received packetized voice signal and converts the packetized noise signal into an output noise signal. When the access network ceases to receive the input voice signal while the call is still ongoing, the access network instructs the egress network to continually output the output noise signal. | 04-29-2010 |
| 20100100911 | System and Method for Delivery of Video-on-Demand - A method of providing video-on-demand content includes receiving a request from a set-top box, and determining the video-on-demand content is not stored locally. The request includes a content identifier for the video-on-demand content. The method further includes identifying a peer likely to have the video-on-demand content, receiving at least a first portion of the video-on-demand content from the peer, and providing the video-on-demand content to the set-top box. | 04-22-2010 |
| 20100100509 | Systems and Methods for Generating Markup-Language Based Expressions from Multi-Modal and Unimodal Inputs - When using finite-state devices to perform various functions, it is beneficial to use finite state devices representing regular grammars with terminals having markup-language-based semantics. By using markup-language-based symbols in the finite state devices, it is possible to generate valid markup-language expressions by concatenating the symbols representing the result of the performed function. The markup-language expression can be used by other applications and/or devices. Finite-state devices are used to convert strings of words and gestures into valid markup-language, for example, XML, expressions that can be used, for example, to provide an application program interface to underlying system applications. | 04-22-2010 |
| 20100100385 | System and Method for Testing a TTS Voice - Disclosed are various elements of a toolkit used for generating a TTS voice for use in a spoken dialog system. The invention in each case may be in the form of the system, a computer-readable medium or a method for generating the TTS voice. An embodiment of the invention relates to a method for preparing a text-to-speech (TTS) voice for testing and verification. The method comprises processing a TTS voice to be ready for testing, synthesizing words utilizing the TTS voice, presenting to a person a smallest possible subset that contains at least N instances of a group of units in the TTS voice, receiving information from the person associated with corrections needed to the TTS voice and making corrections to the TTS voice according to the received information. | 04-22-2010 |
| 20100100381 | System and Method for Automatic Verification of the Understandability of Speech - The present invention relates to a system and method for automatically verifying that a message received from a user is intelligible. In an exemplary embodiment, a message is received from the user. A speech level of the user's message may be measured and compared to a pre-determined speech level threshold to determine whether the measured speech level is below the pre-determined speech level threshold. A signal-to-noise ratio of the user's message may be measured and compared to a pre-determined signal-to-noise ratio threshold to determine whether the measured signal-to-noise ratio of the message is below the pre-determined signal-to-noise ratio threshold. An estimate of intelligibility for the user's message may be calculated and compared to an intelligibility threshold to determine whether the calculated estimate of intelligibility is below the intelligibility threshold. If any of the measured speech level, measured signal-to-noise ratio and calculated estimate of intelligibility of the user's message are determined to be below their respective thresholds, the user may be prompted to repeat at least a portion of the message. | 04-22-2010 |
| 20100100380 | Multitask Learning for Spoken Language Understanding - A system, method and computer-readable medium provide a multitask learning method for intent or call-type classification in a spoken language understanding system. Multitask learning aims at training tasks in parallel while using a shared representation. A computing device automatically re-uses the existing labeled data from various applications, which are similar but may have different call-types, intents or intent distributions to improve the performance. An automated intent mapping algorithm operates across applications. In one aspect, active learning is employed to selectively sample the data to be re-used. | 04-22-2010 |
| 20100100375 | System and Method for Improved Use of Voice Activity Detection - The present invention is a system and method for packetizing actual noise signals, typically background noise, received by an access gateway from a speaking party and transmitting these packetized noise signals via a network to an egress gateway. The egress gateway converts the packetized noise signal into noise signals suitable for output and transmits the output noise signals to a listening party. When the access gateway detects that no voice signal is being received and only a noise signal is being received for a predetermined period of time, the access gateway instructs the egress network to continually transmit output noise signals to the listening party and ceases to transmit packetized noise signals to the egress gateway. | 04-22-2010 |
| 20100100211 | EFFECTIVE DEPLOYMENT OF TEMPORAL NOISE SHAPING (TNS) FILTERS | 04-22-2010 |
| 20100098227 | Method and Apparatus for Voice Mail Notes - A novel method and apparatus for recording an audio note for a voice message stored on a messaging platform are disclosed. | 04-22-2010 |
| 20100098224 | Method and Apparatus for Automatically Building Conversational Systems - A system and method provides a natural language interface to world-wide web content. Either in advance or dynamically, webpage content is parsed using a parsing algorithm. A person using a telephone interface can provide speech information, which is converted to text and used to automatically fill in input fields on a webpage form. The form is then submitted to a database search and a response is generated. Information contained on the responsive webpage is extracted and converted to speech via a text-to-speech engine and communicated to the person. | 04-22-2010 |
| 20100097928 | METHOD AND APPARATUS FOR INCREASING SURVIVABILITY IN IP NETWORKS - A method and apparatus for increasing the capability of a network topology model having a plurality of nodes connected by existing links to maintain service continuity in the presence of faults. The steps of the method include adding new links to the network topology model to protect against single node failures, and adjusting link weights for the network topology model to reduce at least one of a cost of network operation and an imbalance in link utilizations. Preferably, the link weights are adjusted to reduce the imbalance in link utilizations without deteriorating the cost of network operation. The link weights are preferably adjusted to reduce the cost of network operation without increasing the imbalance in link utilizations. Preferably, the link weights are adjusted to reduce the cost of network operation without increasing the imbalance in link utilizations while keeping the utilization for each link below a specific threshold. In addition, links can be added to the network topology model to reduce the cost of network operation. | 04-22-2010 |
| 20100094644 | Microbilling using a trust management system - The present invention provides a microbilling system that integrates with existing billing systems and existing devices. In a preferred embodiment of the invention, the devices store digital certificates with short-lived expiration dates and specifying transaction limits, preferably using a trust management system. A provisioning agent periodically (e.g., once a day) issues the certificates over a secure channel to the devices. When conducting a purchase transaction, the devices exchange certificates via a communication channel (that need not be secure) and the purchasing device issues a digitally signed electronic check which is periodically deposited over an advantageously secure channel with a clearing service. The present invention enables microbilling transactions by embedding liability in the certificates. | 04-15-2010 |
| 20100094632 | System and Method of Developing A TTS Voice - Disclosed herein are various aspects of a toolkit used for generating a TTS voice for use in a spoken dialog system. The embodiments in each case may be in the form of the system, a computer-readable medium or a method for generating the TTS voice. An embodiment of the invention relates to a method of tracking progress in developing a text-to-speech (TTS) voice. The method comprises insuring that a corpus of recorded speech contains reading errors and matches an associated written text, creating a tuple for each utterance in the corpus and tracking progress for each utterance utilizing the tuple. Various parameters may be tracked using the tuple but the tuple provides a means for enabling multiple workers to efficiently process a database of utterance in preparation of a TTS voice. | 04-15-2010 |
| 20100094628 | System and Method for Latency Reduction for Automatic Speech Recognition Using Partial Multi-Pass Results - A system and method is provided for reducing latency for automatic speech recognition. In one embodiment, intermediate results produced by multiple search passes are used to update a display of transcribed text. | 04-15-2010 |
| 20100094591 | Forecasting Outcomes Based on Analysis of Text Strings - A method and a processing device are provided for forecasting whether a record of data for an individual is associated with an outcome. Whether an n-gram associated with one of a group of predictors matches an n-gram included in the record of data is determined. When the n-gram included with the one of the group of predictors matches the n-gram in the record of data, a prediction is made as to whether the record of data is associated with the outcome based on a value assigned to the one of the group of predictors. | 04-15-2010 |
| 20100088160 | Automatic Learning for Mapping Spoken/Text Descriptions of Products onto Available Products - A method, processing device, and machine-readable medium are provided. Costs of states of a state space are calculated. Each state represent one or more available product attributes having zero or more decided attribute values. The calculating is based, at least in part, on training data associated with previously requested and offered products. Determining a next state such that one or more products are available and a sum of values, including a cost of a next state and a cost of a perturbation of one of the one or more requested product attribute values to reach the next state is a minimum value. A value for a product attribute is mapped according to the minimum sum of values and product attribute values of available products. | 04-08-2010 |
| 20100080568 | Optical Swapping of Digitally-Encoded Optical Labels - A method and a device are provided for swapping optical labels in an optical communication network. Optical information, including payload data and label data digitally encoded into the optical information, is received. At least one group of bits within the optical information is selectively inverted to rewrite the label data with new label data without changing the payload data. Each of the at least one group of inverted bits includes at least two bits and all bits of each of the at least one group of inverted bits are contiguous bits. | 04-01-2010 |
| 20100077314 | System and Measured Method for Multilingual Collaborative Network Interaction - Disclosed are systems, methods, and computer readable media for providing a collaborative communication environment. The method embodiment comprises receiving user profiles, establishing a collaborative communication environment where a plurality of users simultaneously interact over a network, converting data to be sent to each user in a collaborative environment based on the respective user's profile, and presenting a localized experience to each user using the converted data. | 03-25-2010 |
| 20100076762 | Coarticulation Method for Audio-Visual Text-to-Speech Synthesis - A method for generating animated sequences of talking heads in text-to-speech applications wherein a processor samples a plurality of frames comprising image samples. The processor reads first data comprising one or more parameters associated with noise-producing orifice images of sequences of at least three concatenated phonemes which correspond to an input stimulus. The processor reads, based on the first data. second data comprising images of a noise-producing entity. The processor generates an animated sequence of the noise-producing entity. | 03-25-2010 |
| 20100076750 | System for Low-Latency Animation of Talking Heads - Methods and apparatus for rendering a talking head on a client device are disclosed. The client device has a client cache capable of storing audio/visual data associated with rendering the talking head. The method comprises storing sentences in a client cache of a client device that relate to bridging delays in a dialog, storing sentence templates to be used in dialogs, generating a talking head response to a user inquiry from the client device, and determining whether sentences or stored templates stored in the client cache relate to the talking head response. If the stored sentences or stored templates relate to the talking head response, the method comprises instructing the client device to use the appropriate stored sentence or template from the client cache to render at least a part of the talking head response and transmitting a portion of the talking head response not stored in the client cache, if any, to the client device to render a complete talking head response. If the client cache has no stored data associated with the talking head response, the method comprises transmitting the talking head response to be rendered on the client device. | 03-25-2010 |
| 20100074115 | System and Method for Designing a Network - A system and computer-readable medium for designing a network are disclosed. A network is designed by a system having modules configured to perform steps that generate the network wherein nodes originate and terminate traffic to keep delay related to node-to-node delay-sensitive communication below a threshold. The computer-readable medium stores instructions for controlling a computing device to design the network. The instructions comprise obtaining an initial network topology including links and traffic routing based on a volume of traffic, allocating a maximum delay to each link in the network topology in proportion to a square root of an imputed cost for each of the links, sizing a bandwidth required for each of the links based on a current traffic routing and at least one of a maximum delay allocated to the link, determining link lengths and rerouting traffic according to shortest paths with respect to the determined link lengths. | 03-25-2010 |
| 20100069109 | Time-Multiplexed, Two Tier Wireless Device and Method Therefor - Network devices are disclosed where transmission of information over a wireless channel by a device is prevented or allowed during a particular time period based upon a classification of the wireless electronic device, and whether the particular time period is associated with that classification. | 03-18-2010 |
| 20100067576 | Method and Apparatus to Prioritize Video Information During Coding and Decoding - A method and apparatus prioritizing video information during coding and decoding. Video information is received and an element of the video information, such as a visual object, video object layer, video object plane or keyregion, is identified. A priority is assigned to the identified element and the video information is encoded into a bitstream, such as a visual bitstream encoded using the MPEG-4 standard, including an indication of the priority of the element. The priority information can then be used when decoding the bitstream to reconstruct the video information | 03-18-2010 |
| 20100058405 | Systems and Methods for Distributing Video on Demand - A method of receiving content includes joining an in-progress multicast stream to receive a first portion of a content. The method further includes sending a request to a peer for a catch-up portion of the content, the request including a deadline for delivery of the content, and receiving the catch-up portion of the content from the peer prior to the deadline. | 03-04-2010 |
| 20100058385 | System and Method for Detecting Closed Captioning and Creating a Closed Captioning Electronic Programming Guide - A set-top box device includes a detector module and an electronic programming guide module. The detector module is configured to detect a closed captioning flag in a video stream, and to cache electronic programming guide information for the video stream if the video stream includes the closed captioning flag. The detector module is further configured to create a closed captioning electronic programming guide including the electronic programming guide information. The electronic programming guide module is in communication with the detector module, and is configured to output the closed captioning electronic programming guide. | 03-04-2010 |
| 20100057894 | Targeted Caching to Reduce Bandwidth Consumption - A system includes a name server, an edge cache server, and a local cache server. The name server is configured to provide an anycast IP address in response to a request for an IP address of an origin hostname from a client system. The edge cache server is configured to respond to the anycast IP address and a unicast IP address and to retrieve content from an origin. The local cache server includes a storage and is configured to respond to the anycast IP address, to retrieve content from the edge cache server, and provide the content to a client system. | 03-04-2010 |
| 20100057805 | System, Method and Computer-Readable Medium for Providing Pattern Matching - A system, method and computer-readable medium are disclosed for identifying representative data using sketches. The method embodiment comprises generating a plurality of vectors from a data set, modifying each of the vectors of the plurality of vectors and selecting one of the plurality of generated vectors according to a comparison of a summed distance between a modified vector associated with the selected generated vector and remaining modified vectors. Modifying the generated vectors may involve reduced each generated vector to a lower dimensional vector. The summed distance then represents a summed distance between the lower dimensional vector and remaining lower dimensional vectors. | 03-04-2010 |
| 20100054344 | System and Method of Filtering Noise - A system and method of removing noise in a bitstream is disclosed. The system and method are most applicable to removing noise in a bitstream wherein the bitstream is encoded after being segmented into portions based on predefined classifications or models. Based on the segment classifications, each segment or portion is encoded with a different encoder associated with the portion model and chosen from a plurality of encoders. The coded bit-stream for each segment includes information regarding which encoder was used to encode that segment. A circuit for removing noise in video content comprises a first filter connected to a first input switch and a first output switch, the first filter being in parallel with a first pass-through line, a second filter connected to a second input switch and a second output switch, the second filter connected in parallel with a second pass-through line, and a third filter connected to a third input switch in a third output switch. The third filter is connected in parallel with a third pass-through line, wherein the first output switch is connected to the second input switch and the second output switch is connected to the third input switch. The first input switch, first output switch, second input switch, second output switch, third input switch, and third output switch are controlled to either filter each video portion or not filter each video portion according to descriptors related to the video content. | 03-04-2010 |
| 20100049523 | SYSTEM AND METHOD FOR CONFIGURING VOICE SYNTHESIS - Systems and methods for providing synthesized speech in a manner that takes into account the environment where the speech is presented. A method embodiment includes, based on a listening environment and at least one other parameter associated with at least one other parameter, selecting an approach from the plurality of approaches for presenting synthesized speech in a listening environment, presenting synthesized speech according to the selected approach and based on natural language input received from a user indicating that an inability to understand the presented synthesized speech, selecting a second approach from the plurality of approaches and presenting subsequent synthesized speech using the second approach. | 02-25-2010 |
| 20100049519 | Recognizing the Numeric Language in Natural Spoken Dialogue - 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. | 02-25-2010 |
| 20100042697 | SYSTEM AND METHOD OF CUSTOMIZING ANIMATED ENTITIES FOR USE IN A MULTIMEDIA COMMUNICATION APPLICATION - In an embodiment, a method is provided for creating a personal animated entity for delivering a multi-media message from a sender to a recipient. An image file from the sender may be received by a server. The image file may include an image of an entity. The sender may be requested to provide input with respect to facial features of the image of the entity in preparation for animating the image of the entity. After the sender provides the input with respect to the facial features of the image of the entity, the image of the entity may be presented as a personal animated entity to the sender to preview. Upon approval of the preview from the sender, the image of the entity may be presented as a sender-selectable personal animated entity for delivering the multi-media message to the recipient. | 02-18-2010 |
| 20100042408 | SYSTEM FOR BANDWIDTH EXTENSION OF NARROW-BAND SPEECH - A system and method are disclosed for extending the bandwidth of a narrowband signal such as a speech signal. The method applies a parametric approach to bandwidth extension but does not require training. The parametric representation relates to a discrete acoustic tube model (DATM). The method comprises computing narrowband linear predictive coefficients (LPCs) from a received narrowband speech signal, computing narrowband partial correlation coefficients (parcors) using recursion, computing M | 02-18-2010 |
| 20100042404 | METHOD FOR BUILDING A NATURAL LANGUAGE UNDERSTANDING MODEL FOR A SPOKEN DIALOG SYSTEM - A method of generating a natural language model for use in a spoken dialog system is disclosed. The method comprises using sample utterances and creating a number of hand crafted rules for each call-type defined in a labeling guide. A first NLU model is generated and tested using the hand crafted rules and sample utterances. A second NLU model is built using the sample utterances as new training data and using the hand crafted rules. The second NLU model is tested for performance using a first batch of labeled data. A series of NLU models are built by adding a previous batch of labeled data to training data and using a new batch of labeling data as test data to generate the series of NLU models with training data that increases constantly. If not all the labeling data is received, the method comprises repeating the step of building a series of NLU models until all labeling data is received. After all the training data is received, at least once, the method comprises building a third NLU model using all the labeling data, wherein the third NLU model is used in generating the spoken dialog service. | 02-18-2010 |
| 20100040204 | Performance Testing of Echo Cancellers Using a White Noise Test Signal - Testing equipment for and a method of performance testing an echo canceller are disclosed. The method includes generating a white noise test signal that includes a plurality of high-level white noise time segments, each of which is separated by a low-level white noise time gap. The generated white noise test signal is transmitted to the echo canceller. At least one echo output signal is received from the echo canceller, and the echo output signal results from the white noise test signal. The level and duration of the received at least one echo output signal are measured. | 02-18-2010 |
| 20100037266 | Multimedia Channel Sharing - An initiating viewer identifies a multimedia channel and submits a request to share the multimedia channel with at least one recipient viewer at another viewer premises. This request is processed by the multimedia receiver of the initiating viewer so as to generate a channel change request for submission to a service provider. In response to the channel share request, the service provider queries the recipient viewer to determine whether the recipient viewer accepts or rejects the offered multimedia channel. If the recipient viewer accepts the multimedia channel, the multimedia channel can be provided to the multimedia receiver of the recipient viewer either for storage for later playback or for immediate playback concurrent with the provision of the multimedia channel to the initiating viewer. Billing for costs associated with the shared multimedia channel is conducted based on billing feedback provided by the initiating viewer. | 02-11-2010 |
| 20100037256 | Multimedia Channel Sharing Across Access Network Boundaries - An initiating viewer identifies a multimedia channel and submits a request to share the multimedia channel with at least one recipient viewer at another viewer premises. This request is processed by the multimedia receiver of the initiating viewer so as to generate a channel change request for submission to a service provider. In response to the channel share request, the service provider queries the recipient viewer to determine whether the recipient viewer accepts or rejects the offered multimedia channel. If the recipient viewer accepts the multimedia channel, the multimedia channel can be provided to the multimedia receiver of the recipient viewer either for storage for later playback or for immediate playback concurrent with the provision of the multimedia channel to the initiating viewer. Billing for costs associated with the shared multimedia channel is conducted based on billing feedback provided by the initiating viewer. | 02-11-2010 |
| 20100030764 | Recommender System Utilizing Collaborative Filtering Combining Explicit and Implicit Feedback with both Neighborhood and Latent Factor Models - Example collaborative filtering techniques provide improved recommendation prediction accuracy by capitalizing on the advantages of both neighborhood and latent factor approaches. One example collaborative filtering technique is based on an optimization framework that allows smooth integration of a neighborhood model with latent factor models, and which provides for the inclusion of implicit user feedback. A disclosed example Singular Value Decomposition (SVD)-based latent factor model facilitates the explanation or disclosure of the reasoning behind recommendations. Another example collaborative filtering model integrates neighborhood modeling and SVD-based latent factor modeling into a single modeling framework. These collaborative filtering techniques can be advantageously deployed in, for example, a multimedia content distribution system of a networked service provider. | 02-04-2010 |
| 20100023828 | IP Multicast with IP Unicast/Multicast Error Correction - A method of delivering digital information includes joining a multicast group, and receiving a segment from a server directed to the multicast group. Further, the method further includes determining a transmission error has occurred resulting in an incomplete segment, and sending an error notification to the server requesting retransmission of at least a portion of the incomplete segment. Additionally, the method includes receiving a retransmission of the at least a portion of the incomplete segment. The at least a portion of the incomplete segment may be received through an IP unicast connection or as a multicast retransmission. | 01-28-2010 |
| 20100020688 | Systems and Methods for Proactive Surge Protection - A system for protecting a network from a traffic surge includes a data collection module, an allocation module, and a traffic flow module. The data collection module is configured to obtain network utilization information for a plurality of traffic flows. The allocation module is configured to determine a bandwidth allocation to minimize a drop probability for the plurality of traffic flows. The traffic flow module is configured to preferentially drop network packets for a traffic flow exceeding the optimal bandwidth allocation. | 01-28-2010 |
| 20100020687 | Proactive Surge Protection - A system for protecting a network from a traffic surge includes a data collection module, an allocation module, and a traffic flow module. The data collection module is configured to obtain network utilization information for a plurality of traffic flows. The allocation module is configured to determine an optimal bandwidth allocation for each of the plurality of traffic flows. The traffic flow module is configured to preferentially drop network packets for a traffic flow exceeding the optimal bandwidth allocation. | 01-28-2010 |
| 20090328122 | METHOD AND APPARATUS FOR PRESENTING MEDIA PROGRAMS - A system that incorporates teachings of the present disclosure may include, for example, a system having a controller to collect one or more temporal actions initiated by each of a plurality of users while presenting a media program to said plurality of users, generate one or more symbolic overlays according to the one or more temporal actions collected for each user, and combine the presentation of the media program with a presentation of the one or more symbolic overlays. Other embodiments are disclosed. | 12-31-2009 |
| 20090322778 | SYSTEM AND METHOD FOR ENCODING AND DECODING USING TEXTURE REPLACEMENT - The invention provides devices and methods that process images. The invention processes a received signal representing information of texture and information of an image, which has the texture removed from at least one region. The image information is encoded to obtain encoded information of the image. An output signal is generated representing the texture information and the encoded image information. In another embodiment, the invention synthesizes texture based on the received texture information, decodes received image information, which is encoded, to obtain a decoded image, and then maps the synthesized texture onto the decoded image. | 12-31-2009 |
| 20090320102 | Methods for Distributing Information Using Secure Peer-to-Peer Communications - A method for providing access to secure peer-to-peer communications to a device can include receiving a request to join an interest group. The request can include a device identification number of the device. The method can further include determining access rights for the device. The access rights can include permission to access shared messages of the interest group. Additionally, the method can include providing an access key to the device. The access key can enable the device to access shared messages of the interest group. | 12-24-2009 |
| 20090316878 | System and Method of Providing a High-Quality Voice Network Architecture Over IP Centrex - A system and method are disclosed for providing high quality sound communications in an IP Centrex environment. The method aspect of the invention comprises, from a network switch, negotiating between a first customer premises equipment (CPE) and a second CPE, the negotiation being related to a possible quality of a call between the first CPE and the second CPE. Next, the switch controls mapping between a dialing plan and a network address, determining a network address of the first CPE and the second CPE and connecting the call between the first CPE and the second CPE. In this manner, the highest quality and broadest bandwidth possible between the first CPE and second CPE through the IP Centrex environment may be used for the call. | 12-24-2009 |
| 20090313025 | Automatic Segmentation in Speech Synthesis - A method and system are disclosed that automatically segment speech to generate a speech inventory. The method includes initializing a Hidden Markov Model (HMM) using seed input data, performing a segmentation of the HMM into speech units to generate phone labels, correcting the segmentation of the speech units. Correcting the segmentation of the speech units includes re-estimating the HMM based on a current version of the phone labels, embedded re-estimating of the HMM, and updating the current version of the phone labels using spectral boundary correction. The system includes modules configured to control a processor to perform steps of the method. | 12-17-2009 |
| 20090300041 | Method and System for Training a Text-to-Speech Synthesis System Using a Specific Domain Speech Database - A method and system are disclosed that train a text-to-speech synthesis system for use in speech synthesis. The method includes generating a speech database of audio files comprising domain-specific voices having various prosodies, and training a text-to-speech synthesis system using the speech database by selecting audio segments having a prosody based on at least one dialog state. The system includes a processor, a speech database of audio files, and modules for implementing the method. | 12-03-2009 |
| 20090299758 | Method and Apparatus for Reducing Access Delay in Discontinuous Transmission Packet Telephony Systems - Systems are disclosed for operating a communications network. The system includes a module to buffer frames of a signal, and a module to determine an access delay. The system also includes a module to compress a portion of the signal based on the access delay by removing a first portion of a frame of the signal and generating an overlap-added segment from a first segment and a second segment of the frame. In another embodiment, the system includes a module to buffer frames of a signal, a module to establish a communication channel with a handset, and a module to determine an access delay. The system also includes a module to compress a portion of the signal based on the access delay by removing a first portion of a frame of the signal and generating an overlap-added segment from a first segment and a second segment of the frame. | 12-03-2009 |
| 20090292529 | SYSTEM AND METHOD OF PROVIDING A SPOKEN DIALOG INTERFACE TO A WEBSITE - Disclosed is a system and 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 converting data from a structured database associated with a website to a structured text data set and a structured task knowledge base, extracting linguistic items from the structured database, and training a spoken dialog service component using at least one of the structured text data, the structured task knowledge base, or the linguistic items. The system includes modules configured to implement the method. | 11-26-2009 |
| 20090290694 | METHODS AND SYSTEM FOR CREATING VOICE FILES USING A VOICEXML APPLICATION - Methods and systems for audio file insertion in spoken dialog code for use in interactive voice services are provided. The method includes identifying an audio tag in spoken dialog code of an interactive voice system, extracting data associated with the audio tag, generating a database query based on the extracted data, and retrieving at least one audio filename associated with an audio file to be played to a user in the interactive voice system, and replacing the extracted data with the audio filename in the spoken dialog code if the audio file associated with the audio filename matches at least a portion of the extracted data. The system includes a processor and modules for performing the steps of the method. | 11-26-2009 |
| 20090281806 | SYSTEM AND METHOD FOR SPELLING RECOGNITION USING SPEECH AND NON-SPEECH INPUT - A system and method for non-speech input or keypad-aided word and spelling recognition is disclosed. The method includes generating an unweighted grammar, selecting a database of words, generating a weighted grammar using the unweighted grammar and a statistical letter model trained on the database of words, receiving speech from a user after receiving the non-speech input and after generating the weighted grammar, and performing automatic speech recognition on the speech and non-speech input using the weighted grammar. If a confidence is below a predetermined level, then the method includes receiving non-speech input from the user, disambiguating possible spellings by generating a letter lattice based on a user input modality, and constraining the letter lattice and generating a new letter string of possible word spellings until a letter string is correctly recognized. | 11-12-2009 |
| 20090276225 | METHOD FOR AUTOMATED SENTENCE PLANNING IN A TASK CLASSIFICATION SYSTEM - The invention relates to a method for sentence planning ( | 11-05-2009 |
| 20090259465 | LOW LATENCY REAL-TIME VOCAL TRACT LENGTH NORMALIZATION - A method and system for training an automatic speech recognition system are provided. The method includes separating training data into speaker specific segments, and for each speaker specific segment, performing the following acts: generating spectral data, selecting a first warping factor and warping the spectral data, and comparing the warped spectral data with a speech model. The method also includes iteratively performing the steps of selecting another warping factor and generating another warped spectral data, comparing the other warped spectral data with the speech model, and if the other warping factor produces a closer match to the speech model, saving the other warping factor as the best warping factor for the speaker specific segment. The system includes modules configured to control a processor in the system to perform the steps of the method. | 10-15-2009 |
| 20090254344 | ACTIVE LABELING FOR SPOKEN LANGUAGE UNDERSTANDING - A spoken language understanding method and system are provided. The method includes classifying a set of labeled candidate utterances based on a previously trained classifier, generating classification types for each candidate utterance, receiving confidence scores for the classification types from the trained classifier, sorting the classified utterances based on an analysis of the confidence score of each candidate utterance compared to a respective label of the candidate utterance, and rechecking candidate utterances according to the analysis. The system includes modules configured to control a processor in the system to perform the steps of the method. | 10-08-2009 |
| 20090248416 | SYSTEM AND METHOD OF SPOKEN LANGUAGE UNDERSTANDING USING WORD CONFUSION NETWORKS - Word lattices that are generated by an automatic speech recognition system are used to generate a modified word lattice that is usable by a spoken language understanding module. In one embodiment, the spoken language understanding module determines a set of salient phrases by calculating an intersection of the modified word lattice, which is optionally preprocessed, and a finite state machine that includes a plurality of salient grammar fragments. | 10-01-2009 |
| 20090232132 | COMMON MOBILITY MANAGEMENT PROTOCOL FOR MULTIMEDIA APPLICATIONS, SYSTEMS AND SERVICES - A framework of a common mobility management protocol for Q.5/16 includes a high level protocol for performing the functions of address resolution, routing, location update and authentication. The common mobility management protocol can be used by existing and future multimedia applications (MA's) to support mobility management for messaging among mobility management authentication function (AuF), home location function (HLF) and visitor location function (VLF) databases/servers, and the corresponding multimedia application functional entities (MAFEs) of the multimedia applications (MA's). The common mobility management protocol may replace, act in concert with or in sequence with existent interworking protocols for the various multimedia applications. Reference point architectures, functional characteristics, features, and capabilities of the protocol are described including call flows and message syntax. The disclosure presents the scope of Q.5/16 and how H.MMS.1 (H.323 Mobility), H.MMS.2 (Global Mobility), and H.MMS.3 (Presence/Instant Messaging Mobility) can be a part of the same common mobility management protocol. | 09-17-2009 |
| 20090222267 | AUTOMATED SENTENCE PLANNING IN A TASK CLASSIFICATION SYSTEM - The invention relates to a task classification system ( | 09-03-2009 |
| 20090213932 | BIDIRECTIONAL PREDICTED PICTURES OR VIDEO OBJECT PLANES FOR EFFICIENT AND FLEXIBLE CODING - A method is provided for decoding a bit stream representing an image that has been encoded The method includes the steps of: performing an entropy decoding of the bit stream to form a plurality of transform coefficients and a plurality of motion vectors; performing an inverse transformation on the plurality of transform coefficients to form a plurality of error blocks; determining a plurality of predicted blocks based on bidirectional motion estimation that employs the motion vectors, wherein the bidirectional motion estimation includes a direct prediction mode and a second prediction mode; and, adding the plurality of error blocks to the plurality of predicted blocks to form the image. The second prediction mode may include forward, backward, and interpolated prediction modes. | 08-27-2009 |
| 20090198493 | System and Method for Unsupervised and Active Learning for Automatic Speech Recognition - A system and method is provided for combining active and unsupervised learning for automatic speech recognition. This process enables a reduction in the amount of human supervision required for training acoustic and language models and an increase in the performance given the transcribed and un-transcribed data. | 08-06-2009 |
| 20090187584 | Query-aware sampling of data streams - A system, method and computer-readable medium provide for assigning sampling methods to each input stream for arbitrary query sets in a data stream management system. The method embodiment comprises splitting all query nodes in a query directed acyclic graph (DAG) having multiple parent nodes into sets of independent nodes having a single parent, computing a grouping set for every node in each set of independent nodes, reconciling each parent node with each child node in each set of independent node, reconciling between multiple child nodes that share a parent node and generating a final grouping set for at least one node describing how to sample an input stream for that node. | 07-23-2009 |
| 20090185692 | System and Method of Retrieving a Watermark Within a Signal - A system and method of retrieving a watermark in a watermarked signal are disclosed. The watermarked signal comprises odd and even overlapped blocks where the watermark is contained in the even blocks. The method comprises, for each k-th even block, subtracting the two adjacent odd numbered blocks from the k-th even block of the watermarked signal to retrieve | 07-23-2009 |
| 20090180645 | SYSTEM AND METHOD FOR DEPLOYING FILTERS FOR PROCESSING SIGNALS - A system, method and computer-readable medium are disclosed for using filters signal processing. The system includes a module that calculates a filter for each of a plurality of frequency bands, a module that groups the filters into a plurality of groups, a module that determines a representative filter for each group of the plurality of groups and a module that uses the representative filter of each group for frequency bands of the each group. The filters are temporal noise shaping filters (TNS) filters. | 07-16-2009 |
| 20090169210 | DIGITAL ENCODING OF LABELS FOR OPTICAL PACKET NETWORKS - Methods and apparatuses are provided for transmitting labels in an optical packet network. Groups of K payload bits are encoded into blocks of N bits by using a code in which each of the groups of K payload bits is represented by a corresponding one of at least two distinct codewords of differing weights to form coded payload packet data, where K and N are integers and K| 07-02-2009 | |
| 20090157736 | MULTIMEDIA INTEGRATION DESCRIPTION SCHEME, METHOD AND SYSTEM FOR MPEG-7 - The invention provides a system and method for integrating multimedia descriptions in a way that allows humans, software components or devices to easily identify, represent, manage, retrieve, and categorize the multimedia content. In this manner, a user who may be interested in locating a specific piece of multimedia content from a database, Internet, or broadcast media, for example, may search for and find the multimedia content. In this regard, the invention provides a system and method that receives multimedia content and separates the multimedia content into separate components which are assigned to multimedia categories, such as image, video, audio, synthetic and text. Within each of the multimedia categories, the multimedia content is classified and descriptions of the multimedia content are generated. The descriptions are then formatted, integrated, using a multimedia integration description scheme, and the multimedia integration description is generated for the multimedia content. The multimedia description is then stored into a database. As a result, a user may query a search engine which then retrieves the multimedia content from the database whose integration description matches the query criteria specified by the user. The search engine can then provide the user a useful search result based on the multimedia integration description. | 06-18-2009 |
| 20090144050 | SYSTEM AND METHOD FOR AUGMENTING SPOKEN LANGUAGE UNDERSTANDING BY CORRECTING COMMON ERRORS IN LINGUISTIC PERFORMANCE - A method and system for automatic speech recognition are disclosed. The method comprises receiving speech from a user, the speech including at least one speech error, increasing the probabilities of closely related words to the at least one speech error and processing the received speech using the increased probabilities. A corpora of data having common words that are mis-stated is used to identify and increase the probabilities of related words. The method applies to at least the automatic speech recognition module and the spoken language understanding module. | 06-04-2009 |
| 20090116689 | SYSTEM AND METHOD OF WATERMARKING A SIGNAL - A system and method of generating a watermarked signal are disclosed. The system segments the signal into overlapping blocks using a window function and processes the overlapping blocks according to whether each block is odd- or even-numbered. The system windows the odd-numbered blocks, modulates the phase of each block in the frequency domain, transforms each modulated block in the time domain, windows each block transformed into the time domain and overlap-adds each odd-numbered block with each even-numbered block to generate the watermarked signal. | 05-07-2009 |
| 20090112845 | SYSTEM AND METHOD FOR LANGUAGE SENSITIVE CONTEXTUAL SEARCHING - A method, system and computer-readable media for searching a database and returning relevant results are disclosed. The method includes the steps of receiving a user query in one language, searching a database based on the user query to obtain one or more results, processing the results according to a local linguistic context association with the user query, and presenting to the user the results with an identifier for each result in which a local linguistic context around a location of the user query is in a second language. | 04-30-2009 |
| 20090112602 | SYSTEM AND METHOD FOR CONTROLLING DEVICES THAT ARE CONNECTED TO A NETWORK - A system, method and computer-readable medium for controlling devices connected to a network. The method includes receiving an utterance from a user for remotely controlling a device in a network; converting the received utterance to text using an automatic speech recognition module; accessing a user profile in the network that governs access to a plurality of devices on the network and identifiers which control a conversion of the text to a device specific control language; identifying based on the text a device to be controlled; converting at least a portion of the text to the device control language; and transmitting the device control language to the identified device, wherein the identified device implements a function based on the transmitted device control language. | 04-30-2009 |
| 20090112600 | SYSTEM AND METHOD FOR INCREASING ACCURACY OF SEARCHES BASED ON COMMUNITIES OF INTEREST - Disclosed are systems, methods and computer-readable media for using a local communication network to generate a speech model. The method includes retrieving for an individual a list of numbers in a calling history, identifying a local neighborhood associated with each number in the calling history, truncating the local neighborhood associated with each number based on the at least one parameter, retrieving a local communication network associated with each number in the calling history and each phone number in the local neighborhood, and creating a language model for the individual based on the retrieved local communication network. The generated language model may be used for improved automatic speech recognition for audible searches as well as other modules in a spoken dialog system. | 04-30-2009 |
| 20090112590 | SYSTEM AND METHOD FOR IMPROVING INTERACTION WITH A USER THROUGH A DYNAMICALLY ALTERABLE SPOKEN DIALOG SYSTEM - Disclosed are systems and methods for dynamically interacting with a user through a spoken dialogue system. A method includes the steps of (1) receiving a user utterance, (2) analyzing the user utterance for a threshold determination of dialect, (3) generating a response that reflects an incremental implementation of the dialect, (4) further varying the perceived implementation of the dialect in subsequent responses by a process of: (a) receiving a subsequent user utterance, (b) determining a modified level of confidence in the dialect based at least in part from the subsequent utterance, (c) generating a subsequent response that implements an incremental variation according to the modified level of confidence. | 04-30-2009 |
| 20090112585 | TIMING OF SPEECH RECOGNITION OVER LOSSY TRANSMISSION SYSTEMS - Recognizing a stream of speech received as speech vectors over a lossy communications link includes constructing for a speech recognizer a series of speech vectors from packets received over a lossy packetized transmission link, wherein some of the packets associated with each speech vector are lost or corrupted during transmission. Each constructed speech vector is multi-dimensional and includes associated features. After waiting for a predetermined time, speech vectors are generated and potentially corrupted features within the speech vector are indicated to the speech recognizer when present. Speech recognition is attempted at the speech recognizer on the speech vectors when corrupted features are present. This recognition may be based only on certain or valid features within each speech vector. Retransmission of a missing or corrupted packet is requested when corrupted values are indicated by the indicating step and when the attempted recognition step fails. | 04-30-2009 |
| 20090094036 | SYSTEM AND METHOD OF HANDLING PROBLEMATIC INPUT DURING CONTEXT-SENSITIVE HELP FOR MULTI-MODAL DIALOG SYSTEMS - A method of presenting a multi-modal help dialog move to a user in a multi-modal dialog system is disclosed. The method comprises presenting an audio portion of the multi-modal help dialog move that explains available ways of user inquiry and presenting a corresponding graphical action performed on a user interface associated with the audio portion. The multi-modal help dialog move is context-sensitive and uses current display information and dialog contextual information to present a multi-modal help move that is currently related to the user. A user request or a problematic dialog detection module may trigger the multi-modal help move. | 04-09-2009 |
| 20090094035 | METHOD AND SYSTEM FOR PRESELECTION OF SUITABLE UNITS FOR CONCATENATIVE SPEECH - A system and method for improving the response time of text-to-speech synthesis utilizes “triphone contexts” (i.e., triplets comprising a central phoneme and its immediate context) as the basic unit, instead of performing phoneme-by-phoneme synthesis. The method comprises a method of generating a triphone preselection cost database for use in speech synthesis, the method comprising 1) selecting a triphone sequence u | 04-09-2009 |
| 20090092190 | METHODS AND APPARATUS FOR INTEGRATING EXTERNAL APPLICATIONS INTO AN MPEG-4 SCENE - A method of decoding, composing and rendering a scene. First information is obtained, the first information including a part of a MPEG-4 BIFS scene description stream and at least one coded MPEG-4 media stream. The first information is decoded by invoking a BIFS scene decoder and one or more specific media decoders that are required by the scene. Second information is obtained, the second information including a second part of a BIFS scene description stream that contains a reference to an external application. The second information is decoded by invoking the BIFS scene decoder and an external application decoder. An integrated scene is composed, the integrated scene including one or more decoded MPEG-4 media objects and one or more external application objects specified in the decoded scene descriptions streams. The composed integrated scene is rendered on a display. | 04-09-2009 |
| 20090092155 | METHOD AND APPARATUS FOR CONTROLLING ACCESS TO A COMMUNICATION CHANNEL - A method and an apparatus provide for controlled access to a shared communication medium. Time slots on a forward channel include information regarding status useful for remote units to determine whether a reverse channel is available for seizure. Additionally, information along the forward channel provides guidance to the remote units to control attempts to seize the reverse channel. In one embodiment a remote unit divides a data package into a plurality of portions and attempts to seize the reverse channel using a single portion of the data package which corresponds to one time slot on the reverse channel. It then waits until it receives notification along the forward channel that the first data portion was successfully received before it attempts to send any of the remainder of its data in consecutive time slots on the reverse channel. | 04-09-2009 |
| 20090070311 | SYSTEM AND METHOD USING A DISCRIMINATIVE LEARNING APPROACH FOR QUESTION ANSWERING - Disclosed are systems, methods, and computer readable media for answers to natural language questions. The method embodiment comprises training a lexical association model between a question and a first set of one or more possible answers, training a semantic association model between a question and a second set of one or more possible answers, receiving a user question containing at least one query word, parsing the user question syntactically and semantically, formulating a query from the parsed user question containing at least one query word, expanding the query based on the lexical association model and the semantic association model, weighting the at least one query word according to its importance when answering the user question, and returning an answer based on the weighted at least one query word, the lexical association model, and the semantic association model. Other features include using question-answer pairs mined to train the models and returning a plurality of answers in an order based on the lexical association model and the semantic association model. | 03-12-2009 |
| 20090070113 | SYSTEM FOR HANDLING FREQUENTLY ASKED QUESTIONS IN A NATURAL LANGUAGE DIALOG SERVICE - A voice-enabled help desk service is disclosed. The service comprises an automatic speech recognition module for recognizing speech from a user, a spoken language understanding module for understanding the output from the automatic speech recognition module, a dialog management module for generating a response to speech from the user, a natural voices text-to-speech synthesis module for synthesizing speech to generate the response to the user, and a frequently asked questions module. The frequently asked questions module handles frequently asked questions from the user by changing voices and providing predetermined prompts to answer the frequently asked question. | 03-12-2009 |
| 20090063561 | MEDIA MANAGEMENT BASED ON DERIVED QUANTITATIVE DATA OF QUALITY - Disclosed are systems, methods, and computer readable media for media management based on derived quantitative data of quality. The method embodiment comprises receiving a request for a media file, identifying one or more media files associated with the request, measuring at least one audio or visual quality associated with each media file by analyzing at least one of: compression artifacts or grading for each media file, generating quantitative data based on the measured at least one audio or visual quality for each media file, and returning the quantitative data associated with each media file. Other features include the ability to compare, archive, filter, sort and select media files based on the quantitative data. | 03-05-2009 |
| 20090063375 | SYSTEM AND METHOD FOR COMPILING RULES CREATED BY MACHINE LEARNING PROGRAM - A system, a method, and a machine-readable medium are provided. A group of linear rules and associated weights are provided as a result of machine learning. Each one of the group of linear rules is partitioned into a respective one of a group of types of rules. A respective transducer for each of the linear rules is compiled. A combined finite state transducer is created from a union of the respective transducers compiled from the linear rules. | 03-05-2009 |
| 20090063153 | SYSTEM AND METHOD FOR BLENDING SYNTHETIC VOICES - A system and method for generating a synthetic text-to-speech TTS voice are disclosed. A user is presented with at least one TTS voice and at least one voice characteristic. A new synthetic TTS voice is generated by blending a plurality of existing TTS voices according to the selected voice characteristics. The blending of voices involves interpolating segmented parameters of each TTS voice. Segmented parameters may be, for example, prosodic characteristics of the speech such as pitch, volume, phone durations, accents, stress, mis-pronunciations and emotion. | 03-05-2009 |
| 20090063145 | Combining active and semi-supervised learning for spoken language understanding - Combined active and semi-supervised learning to reduce an amount of manual labeling when training a spoken language understanding model classifier. The classifier may be trained with human-labeled utterance data. Ones of a group of unselected utterance data may be selected for manual labeling via active learning. The classifier may be changed, via semi-supervised learning, based on the selected ones of the unselected utterance data. | 03-05-2009 |
| 20090063144 | SYSTEM AND METHOD FOR PROVIDING A COMPENSATED SPEECH RECOGNITION MODEL FOR SPEECH RECOGNITION - An automatic speech recognition (ASR) system and method is provided for controlling the recognition of speech utterances generated by an end user operating a communications device. The ASR system and method can be used with a communications device that is used in a communications network. The ASR system can be used for ASR of speech utterances input into a mobile device, to perform compensating techniques using at least one characteristic and for updating an ASR speech recognizer associated with the ASR system by determined and using a background noise value and a distortion value that is based on the features of the mobile device. The ASR system can be used to augment a limited data input capability of a mobile device, for example, caused by limited input devices physically located on the mobile device. | 03-05-2009 |
| 20090059905 | SYSTEM AND METHOD OF PROVIDING A HIGH-QUALITY VOICE NETWORK ARCHITECTURE - Embodiments of the invention include a system and method for providing high quality voice/sound communications over a local loop of a telephone network. The method aspect of the invention comprises receiving a voice signal, digitizing the voice signal into a high quality voice signal, utilizing sampling rates greater than 8000 samples per second and/or sample sizes greater than 8 bits per sample, negotiating voice processing characteristics between a customer premises equipment and a network element such as a softswitch, receiving speech from a user at a customer premises equipment according to the negotiation, converting the received speech into high bandwidth signal and transmitting the high bandwidth signal to a telephone local loop, transmitting the high bandwidth signal from the local loop to wideband node that packetizes the high bandwidth signal for transmission to a packet network and receiving the packetized signal from the packet network at a switch that switches between an on-network or off-network status. A voice over IP platform may also be used to route packetized signals from the packet network to either the telephone network or another packet network. | 03-05-2009 |
| 20090043585 | SYSTEM AND METHOD FOR PERFORMING SPEECH SYNTHESIS WITH A CACHE OF PHONEME SEQUENCES - Disclosed are systems, methods, and computer readable media for performing speech synthesis. The method embodiment comprises applying a first part of a speech synthesizer to a text corpus to obtain a plurality of phoneme sequences, the first part of the speech synthesizer only identifying possible phoneme sequences, for each of the obtained plurality of phoneme sequences, identifying joins that would be calculated to synthesize each of the plurality of respective phoneme sequences, and adding the identified joins to a cache for use in speech synthesis. | 02-12-2009 |
| 20090019009 | SYSTEMS, METHODS AND COMPUTER PROGRAM PRODUCTS FOR SEARCHING WITHIN MOVIES (SWiM) - Disclosed are systems, methods and computer-readable media for processing a series of media files into a searchable format. The method includes generating a media database by processing each of a plurality of programs. The steps of the method include extracting a subtitle track from each of the programs, retrieving at least one frame associated with the subtitle track, adding metadata to the extracted subtitle track and at least one frame, processing the subtitle track, program statistics and at least one frame in a media database. Another aspect includes receiving a user query associated with dialog in a program, searching the media database and presenting a listing of results, receiving a user selection or program from their listing and transmitting at least one frame, a portion of associated subtitle track and prompts for ordering the program. | 01-15-2009 |
| 20090018819 | TRACKING CHANGES IN STRATIFIED DATA-STREAMS - Disclosed are systems, methods, and computer readable media for detecting and coordinating changes in stratified data streams. The method embodiment comprises receiving one or more data streams, each data stream comprising at least one lexical item and having at least one metavalue, detecting a change in a frequency of the at least one lexical item for each metavalue separately, coordinating the change in frequency of the at least one lexical item with changes in frequencies of lexical items associated with the at least one lexical item by grouping the at least one lexical item and the associated lexical items over time and across at least one metavalue, wherein end grouping is a coordinated change-event, and presenting a summarization of the coordinated change-event to a user. | 01-15-2009 |
| 20090006088 | SYSTEM AND METHOD OF PERFORMING SPEECH RECOGNITION BASED ON A USER IDENTIFIER - Speech recognition models are dynamically re-configurable based on user information, application information, background information such as background noise and transducer information such as transducer response characteristics to provide users with alternate input modes to keyboard text entry. Word recognition lattices are generated for each data field of an application and dynamically concatenated into a single word recognition lattice. A language model is applied to the concatenated word recognition lattice to determine the relationships between the word recognition lattices and repeated until the generated word recognition lattices are acceptable or differ from a predetermined value only by a threshold amount. These techniques of dynamic re-configurable speech recognition provide for deployment of speech recognition on small devices such as mobile phones and personal digital assistants as well environments such as office, home or vehicle while maintaining the accuracy of the speech recognition. | 01-01-2009 |
| 20080319763 | SYSTEM AND DIALOG MANAGER DEVELOPED USING MODULAR SPOKEN-DIALOG COMPONENTS - A dialog manager and spoken dialog service having a dialog manager generated according to a method comprising selecting a top level flow controller based on application type, selecting available reusable subdialogs for each application part, developing a subdialog for each application part not having an available subdialog and testing and deploying the spoken dialog service using the selected top level flow controller, selected reusable subdialogs and developed subdialogs. The dialog manager capable of handling context shifts in a spoken dialog with a user. Application dependencies are established in the top level flow controller thus enabling the subdialogs to be reusable and to be capable of managing context shifts and mixed initiative dialogs. | 12-25-2008 |
| 20080319745 | METHOD AND DEVICE FOR PROVIDING SPEECH-TO-TEXT ENCODING AND TELEPHONY SERVICE - A machine-readable medium and a network device are provided for speech-to-text translation. Speech packets are received at a broadband telephony interface and stored in a buffer. The speech packets are processed and textual representations thereof are displayed as words on a display device. Speech processing is activated and deactivated in response to a command from a subscriber. | 12-25-2008 |
| 20080319741 | SYSTEM AND METHOD FOR IMPROVING ROBUSTNESS OF SPEECH RECOGNITION USING VOCAL TRACT LENGTH NORMALIZATION CODEBOOKS - Disclosed are systems, methods, and computer readable media for performing speech recognition. The method embodiment comprises selecting a codebook from a plurality of codebooks with a minimal acoustic distance to a received speech sample, the plurality of codebooks generated by a process of (a) computing a vocal tract length for a each of a plurality of speakers, (b) for each of the plurality of speakers, clustering speech vectors, and (c) creating a codebook for each speaker, the codebook containing entries for the respective speaker's vocal tract length, speech vectors, and an optional vector weight for each speech vector, (2) applying the respective vocal tract length associated with the selected codebook to normalize the received speech sample for use in speech recognition, and (3) recognizing the received speech sample based on the respective vocal tract length associated with the selected codebook. | 12-25-2008 |
| 20080319733 | SYSTEM AND METHOD TO DYNAMICALLY MANIPULATE AND DISAMBIGUATE CONFUSABLE SPEECH INPUT USING A TABLE - Disclosed are systems, methods, and computer-readable media for disambiguating confusable speech using a table. The method embodiment provides assigning an identifier to each of at least one portion of received speech, querying a table to determine whether at least one entry is associated with the identifier, and if multiple entries are associated in the table with the identifier, then disambiguating between the multiple entries by generating a prompt to the user. Additional features include associating table entries that are not acoustically similar as confusable, presenting the items in the prompt in a sorted order, and dynamically modifying entries in the table. | 12-25-2008 |
| 20080313534 | SYSTEM AND METHOD FOR TEXT TRANSLATIONS AND ANNOTATION IN AN INSTANT MESSAGING SESSION - A system and method for translating received input from a sender to recipient in an instant messaging dialog is disclosed. The method comprises receiving instant messaging input from a sender for recipient, wherein the instant messaging input comprises at least one subculture specific term. A category is identified the defines a difference between the sender and the recipient and the received instant messaging input is modified from the sender by generating an output associated with the least one subculture specific term and based on the identified category. Multiple recipients in a chat session may also each receive a translated or annotated message according to characteristics of each individual recipient. | 12-18-2008 |
| 20080312930 | METHOD AND SYSTEM FOR ALIGNING NATURAL AND SYNTHETIC VIDEO TO SPEECH SYNTHESIS - According to MPEG- | 12-18-2008 |
| 20080312924 | SYSTEM AND METHOD FOR TRACKING PERSONS OF INTEREST VIA VOICEPRINT - Disclosed are systems, methods, and computer readable media for tracking a person of interest. The method embodiment comprises identifying a person of interest, capturing a voiceprint of the person of interest, comparing a received voiceprint of a caller with the voiceprint of the person of interest, and tracking the caller if the voiceprint of the caller is a substantial match to the voiceprint of the person of interest. | 12-18-2008 |
| 20080306743 | SYSTEM AND METHOD OF USING MODULAR SPOKEN-DIALOG COMPONENTS - A system and method are disclosed for switching contexts within a spoken dialog between a user and a spoken dialog system. The spoken dialog system utilizes modular subdialogs that are invoked by at least one flow controller that is a finite state model and that associated with a dialog manager. The spoken dialog system includes a dialog manager with a flow controller and a reusable subdialog module. The method includes, while the spoken dialog is being controlled by the subdialog module that was invoked by the flow controller, receiving context-changing input associated with speech from a user that changes a dialog context and comparing the context-changing input to at least one context shift. And, if any of the context shifts are activated by the comparing step, then passing control of the spoken dialog to the flow controller with context shift message and destination state. | 12-11-2008 |
| 20080306737 | SYSTEMS AND METHODS FOR CLASSIFYING AND REPRESENTING GESTURAL INPUTS - Gesture and handwriting recognition agents provide possible interpretations of electronic ink. Recognition is performed on both individual strokes and combinations of strokes in the input ink lattice. The interpretations of electronic ink are classified and encoded as symbol complexes where symbols convey specific attributes of the contents of the stroke. The use of symbol complexes to represent strokes in the input ink lattice facilitates reference to sets of entities of a specific type. | 12-11-2008 |
| 20080300877 | SYSTEM AND METHOD FOR TRACKING FRAUDULENT ELECTRONIC TRANSACTIONS USING VOICEPRINTS - Disclosed are systems, methods, and computer readable media for comparing customer voice prints with a database of known fraudulent voice signatures and continually updating the database to decrease the risk of identity theft. The method embodiment comprises comparing a received voice signal against a database of known fraudulent voice signatures, denying the caller's transaction if the voice signal substantially matches the database of known fraudulent voice signatures, adding the caller's voice signal to the database of known fraudulent voice signatures if the voice signal does not substantially match a separate speaker verification database and received additional information is not verified. | 12-04-2008 |
| 20080300871 | METHOD AND APPARATUS FOR IDENTIFYING ACOUSTIC BACKGROUND ENVIRONMENTS TO ENHANCE AUTOMATIC SPEECH RECOGNITION - Disclosed are systems, methods, and computer readable media for identifying an acoustic environment of a caller. The method embodiment comprises analyzing acoustic features of a received audio signal from a caller, receiving meta-data information, classifying a background environment of the caller based on the analyzed acoustic features and the meta-data, selecting an acoustic model matched to the classified background environment from a plurality of acoustic models, and performing speech recognition as the received audio signal using the selected acoustic model. | 12-04-2008 |
| 20080288244 | METHOD AND SYSTEM FOR AUTOMATICALLY DETECTING MORPHEMES IN A TASK CLASSIFICATION SYSTEM USING LATTICES - In an embodiment, a lattice of phone strings in an input communication of a user may be recognized, wherein the lattice may represent a distribution over the phone strings. Morphemes in the input communication of the user may be detected using the recognized lattice. Task-type classification decisions may be made based on the detected morphemes in the input communication of the user. | 11-20-2008 |
| 20080285726 | IP Voice Call Surveillance Through Use Of Non-Dedicated IP Phone With Signal Alert Provided To Indicate Content Of Incoming Call Prior To An Answer As Being A Monitored Call - Surveillance of IP telephony may be performed through the use of conventional telephone equipment, according to principles of the invention while preventing giving indication to the monitored phone by alerting the user of the monitoring phone to such surveillance use prior to pick up by an agent for engagement of the monitoring phone in response to the alert. Such alerts may assume many forms such as ringing, visual indicators, data readouts, activating ancillary equipment, various flags, etc. This alert prior to surveillance is distinct from alerts used for normal non-surveillance calls, which the monitoring phone is capable of receiving. | 11-20-2008 |
| 20080285593 | Location system and communication system - A location system comprises a plurality of transponders whose locations are detectable by a base system. The base system interrogates ( | 11-20-2008 |
| 20080275908 | SYSTEM, METHOD AND COMPUTER-READABLE MEDIUM FOR PROVIDING PATTERN MATCHING - A system, method and computer-readable medium are disclosed for identifying representative data using sketches. The method embodiment comprises generating a plurality of vectors from a data set, modifying each of the vectors of the plurality of vectors and selecting one of the plurality of generated vectors according to a comparison of a summed distance between a modified vector associated with the selected generated vector and remaining modified vectors. Modifying the generated vectors may involve reduced each generated vector to a lower dimensional vector. The summed distance then represents a summed distance between the lower dimensional vector and remaining lower dimensional vectors. | 11-06-2008 |
| 20080270130 | SYSTEMS AND METHODS FOR REDUCING ANNOTATION TIME - Systems and methods for annotating speech data. The present invention reduces the time required to annotate speech data by selecting utterances for annotation that will be of greatest benefit. A selection module uses speech models, including speech recognition models and spoken language understanding models, to identify utterances that should be annotated based on criteria such as confidence scores generated by the models. These utterances are placed in an annotation list along with a type of annotation to be performed for the utterances and an order in which the annotation should proceed. The utterances in the annotation list can be annotated for speech recognition purposes, spoken language understanding purposes, labeling purposes, etc. The selection module can also select utterances for annotation based on previously annotated speech data and deficiencies in the various models. | 10-30-2008 |
| 20080267368 | METHOD AND APPARATUS FOR VOICE MAIL NOTES - A novel method and apparatus for recording an audio note for a voice message stored on a messaging platform are disclosed. | 10-30-2008 |
| 20080257284 | SYSTEM AND METHOD FOR THE CO-GENERATION OF FUEL HAVING A CLOSED-LOOP ENERGY CYCLE - A system is provided that draws heat from an open-loop engine cycle into a closed-loop working fluid circulatory system that utilizes computer-aided feedback mechanisms. The closed-loop working fluid draws engine heat from multiple sources: exhaust stack gases, the engine block, the engine transmission, and the engine headers and exhaust manifold near the valves. Heat exchangers are arranged in an ascending pattern according to the temperature of the heat at each heat generating location of the open-loop engine cycle. A wankel or similar type engine receives the heated working fluid and rotates a shaft connected to a generator to generate electricity. An electrolysis unit is powered by the generated electricity and separates water into hydrogen and oxygen. A reformation unit receives fuel such as diesel and the generated hydrogen to reform the fuel prior to injection into the engine for combustion. Oxygen from hydrolysis is combined with ambient air to increase combustion efficiency and reduce harmful emissions. | 10-23-2008 |
| 20080256214 | Subscription-based priority interactive help services on the internet - The present invention includes a method and apparatus for providing an e-help service over a network. The e-help service provides one or more action sequences, i.e., recommended courses of action, for specialized circumstances over a network, such as an Internet Protocol network. Subscribers subscribe to specific application areas, such as one or more application areas related to a subscriber's industry. The e-help service provider maintains information pertaining to application areas in one or more databases. When a user activates the e-help service, information corresponding to the present conditions of the user's circumstance is transmitted to the e-help service provider. The e-help service provider identifies one or more action sequences based upon a statistical analysis of the information received from the user and information stored in a database corresponding to the application area of the user. The action sequences having a high probability of success are transmitted to the user and provide one or more recommended courses of action. | 10-16-2008 |
| 20080255954 | E-coupon service for location-aware mobile commerce which determines whether to supply requested e-coupons based on the number of requests received in a processing cycle, and a threshold number of requests required to make expected returns from redeemed coupons greater than advertising fees - A conditional e-coupon distribution method distributes e-coupons predefined by sellers to mobile users only if the number of mobile users requesting such e-coupons equals or exceeds a threshold. The method receives a request to browse e-coupons from a mobile user. The method receives the location of the mobile user and determines a plurality of sellers local to the mobile electronic device and a plurality of corresponding e-coupons available from the local sellers. The method receives a request for a particular e-coupon from a seller and authorizes the provision of said e-coupon to the mobile user. At the end of a processing cycle, the mobile user receives the requested e-coupon if all conditions, such as a period of time and threshold, have been met. A computer-usable medium having computer-readable program code embodied therein allows for storage of the method. | 10-16-2008 |
| 20080250091 | CUSTOM CHARACTER-CODING COMPRESSION FOR ENCODING AND WATERMARKING MEDIA CONTENT - An apparatus for compressing media content is disclosed. The apparatus divides the media content into at least three predetermined portions, compresses each of the at least three portions using one of at least three different compression algorithms and makes the at least three compressed predetermined portions publicly available. Making the portions publicly available includes, for example, transmitting the portions over a computer network such as the Internet. | 10-09-2008 |
| 20080247519 | METHOD FOR DIALOG MANAGEMENT - A spoken dialog system and method having a dialog management module are disclosed. The dialog management module includes a plurality of dialog motivators for handling various operations during a spoken dialog. The dialog motivators comprise an error handling, disambiguation, assumption, confirmation, missing information, and continuation. The spoken dialog system uses the assumption dialog motivator in either a-priori or a-posteriori modes. A-priori assumption is based on predefined requirements for the call flow and a-posteriori assumption can work with the confirmation dialog motivator to assume the content of received user input and confirm received user input. | 10-09-2008 |
| 20080247034 | Fast Dynamic Gain Control in a Bidirectionally-Pumped Raman Fiber Amplifier - The present invention provides methods and apparatuses for controlling a gain of a bidirectionally-pumped Raman fiber amplifier having both forward optical pumps and backward optical pumps. The overall gain is controlled by adjusting the forward optical pumps, while the power levels of the backward optical pumps are essentially fixed. Gain circuitry operates in an opened loop configuration and uses a predetermined function relating a power variation of at least one wavelength region with a pump power adjustment for at least one forward optical pump. Two approximate linear relationships between the input signal power variations and the required pump power adjustments are utilized in controlling the Raman fiber amplifier. Each approximate linear relationship includes at least one linear coefficient that relates a power variation for a specific wavelength region and a power adjustment of a specific Raman pump. | 10-09-2008 |
| 20080243484 | SYSTEMS AND METHODS FOR GENERATING WEIGHTED FINITE-STATE AUTOMATA REPRESENTING GRAMMARS - A context-free grammar can be represented by a weighted finite-state transducer. This representation can be used to efficiently compile that grammar into a weighted finite-state automaton that accepts the strings allowed by the grammar with the corresponding weights. The rules of a context-free grammar are input. A finite-state automaton is generated from the input rules. Strongly connected components of the finite-state automaton are identified. An automaton is generated for each strongly connected component. A topology that defines a number of states, and that uses active ones of the non-terminal symbols of the context-free grammar as the labels between those states, is defined. The topology is expanded by replacing a transition, and its beginning and end states, with the automaton that includes, as a state, the symbol used as the label on that transition. The topology can be fully expanded or dynamically expanded as required to recognize a particular input string. | 10-02-2008 |
| 20080228825 | SYSTEM AND METHOD OF ORGANIZING DATA TO FACILITATE ACCESS AND STREAMING - File formats systems and methods are disclosed that provide a framework that integrates concepts, such as objects based audio-visual representation, meta-data and object oriented programming, to achieve a flexible and generic representation of the audiovisual information and the associated methods to operate on the audiovisual information. A system and method are disclosed for storing data processed from presentation data. The data is stored according to a method comprising coding input presentation data by identifying objects from within the presentation data, coding each object individually and organizing the coded data into access layer data units. The access layer data units are stored throughout a plurality of segments, each segment comprising a segment table in a header portion thereof and those access layer data units that are members of the respective segment, there being one entry in the segment table for each access layer data unit therein. A plurality of extended segments are also stored, each of the extended segments further comprising one or more of the access layer data units that include protocol specific data, the extended segments each represented by a extended segment header. The data of an accessible object is also stored, including an accessible object header and identifiers of the plurality of extended segments, each of the extended segments being a member of the same object. | 09-18-2008 |
| 20080222574 | GRAPHICAL USER INTERFACE GRAPHICS-BASED INTERPOLATED ANIMATION PERFORMANCE - An arrangement provides for displaying an object, such as a drawn object, or a database search result, based on a graphical user interface. A first display window is provided for specifying attributes of an object. A second window is provided for spatially inserting anchors for the object, where each anchor specifies a desired characteristic of the object, such as a pose of a face. A third window is provided for the desired object display. The anchors are placed in the second window with the aid of a controlled cursor. Placement of the cursor in the second window also controls the displayed object in the third window, which is developed based on the placement of the cursor in the second window relative to the anchors. | 09-11-2008 |
| 20080222555 | GRAPHICAL USER INTERFACE GRAPHICS-BASED INTERPOLATED ANIMATION PERFORMANCE - An arrangement provides for displaying an object, such as a drawn object, or a database search result, based on a graphical user interface. A first display window is provided for specifying attributes of an object. A second window is provided for spatially inserting anchors for the object, where each anchor specifies a desired characteristic of the object, such as a pose of a face. A third window is provided for the desired object display. The anchors are placed in the second window with the aid of a controlled cursor. Placement of the cursor in the second window also controls the displayed object in the third window, which is developed based on the placement of the cursor in the second window relative to the anchors. | 09-11-2008 |
| 20080221904 | COARTICULATION METHOD FOR AUDIO-VISUAL TEXT-TO-SPEECH SYNTHESIS - A method for generating animated sequences of talking heads in text-to-speech applications wherein a processor samples a plurality of frames comprising image samples. The processor reads first data comprising one or more parameters associated with noise-producing orifice images of sequences of at least three concatenated phonemes which correspond to an input stimulus. The processor reads, based on the first data. second data comprising images of a noise-producing entity. The processor generates an animated sequence of the noise-producing entity. | 09-11-2008 |
| 20080221887 | SYSTEMS AND METHODS FOR DYNAMIC RE-CONFIGURABLE SPEECH RECOGNITION - Speech recognition models are dynamically re-configurable based on user information, background information such as background noise and transducer information such as transducer response characteristics to provide users with alternate input modes to keyboard text entry. The techniques of dynamic re-configurable speech recognition provide for deployment of speech recognition on small devices such as mobile phones and personal digital assistants as well environments such as office, home or vehicle while maintaining the accuracy of the speech recognition. | 09-11-2008 |
| 20080215339 | SYSTEM AND METHOD OF CODING SOUND SIGNALS USING SOUND ENHANCMENT - A system and method of processing sound signals are disclosed. In one embodiment, a speech coder applies a first sound signal enhancement process to a first part of a sound signal and applies a second sound signal enhancement process to a second part of the sound signal. The sound signal is then coded using the enhanced first part of the sound signal and the enhanced first part of the sound signal and the enhanced sound part of the sound signal. Examples of the portions of the sound signal that are separately processed include an excitation signal component and a spectral component of the sound signal. | 09-04-2008 |
| 20080215328 | METHOD AND SYSTEM FOR AUTOMATICALLY DETECTING MORPHEMES IN A TASK CLASSIFICATION SYSTEM USING LATTICES - The invention concerns a method and system for detecting morphemes in a user's communication. The method may include recognizing a lattice of phone strings from the user's input communication, the lattice representing a distribution over the phone strings, and detecting morphemes in the user's input communication using the lattice. The morphemes may be acoustic and/or non-acoustic. The morphemes may represent any unit or sub-unit of communication including phones, diphones, phone-phrases, syllables, grammars, words, gestures, tablet strokes, body movements, mouse clicks, etc. The training speech may be verbal, non-verbal, a combination of verbal and non-verbal, or multimodal. | 09-04-2008 |
