Patent application number | Description | Published |
20140303983 | AUTHENTICATION FOR RECOGNITION SYSTEMS - Embodiments include a method, apparatus, and computer program product for authentication for speech recognition. The method can include sensing an authentication device with a target device. One or more decoded voice commands can be processed after verification of the authentication device by the target device. Further, one or more decoded voice commands can be executed by the target device. | 10-09-2014 |
20140304205 | COMBINING OF RESULTS FROM MULTIPLE DECODERS - Embodiments include a method, apparatus, and a computer program product for combining results from multiple decoders. For example, the method can include generating a network of paths based on one or more outputs associated with each of the multiple decoders. The network of paths can be scored to find an initial path with the highest path score based on scores associated with the one or more outputs. A weighting factor can be calculated for each of the multiple decoders based on a number of outputs from each of the multiple decoders included in the initial path with the highest path score. Further, the network of paths can be re-scored to find a new path with the highest path score based on the scores associated with the one or more outputs and the weighting factor for each of the multiple decoders. | 10-09-2014 |
20150106405 | HIDDEN MARKOV MODEL PROCESSING ENGINE - A method, apparatus, and tangible computer readable medium for processing a Hidden Markov Model (HMM) structure are disclosed herein. For example, the method includes receiving Hidden Markov Model (HMM) information from an external system. The method also includes processing back pointer data and first HMM states scores for one or more NULL states in the HMM information. Second HMM state scores are processed for one or more non-NULL states in the HMM information based on at least one predecessor state. Further, the method includes transferring the second HMM state scores to the external system. | 04-16-2015 |
Patent application number | Description | Published |
20140129217 | Senone Scoring For Multiple Input Streams - Embodiments of the present invention include an apparatus, method, and system for calculating senone scores for multiple concurrent input speech streams. The method can include the following: receiving one or more feature vectors from one or more input streams; accessing the acoustic model one senone at a time; and calculating separate senone scores corresponding to each incoming feature vector. The calculation uses a single read access to the acoustic model for a single senone and calculates a set of separate senone scores for the one or more feature vectors, before proceeding to the next senone in the acoustic model. | 05-08-2014 |
20140180690 | Hybrid Hashing Scheme for Active HMMS - Embodiments of the present invention include a data storage device and a method for storing data in a hash table. The data storage device can include a first memory device, a second memory device, and a processing device. The first memory device is configured to store one or more data elements. The second memory device is configured to store one or more status bits at one or more respective table indices. In addition, each of the table indices is mapped to a corresponding table index in the first memory device. The processing device is configured to calculate one or more hash values based on the one or more data elements. | 06-26-2014 |
20140180694 | Phoneme Score Accelerator - Embodiments of the present invention include an acoustic processing device and a method for traversing a Hidden Markov Model (HMM). The acoustic processing device can include a senone scoring unit (SSU), a memory device, a HMM module, and an interface module. The SSU is configured to receive feature vectors from an external computing device and to calculate senones. The memory device is configured to store the senone scores and HMM information, where the HMM information includes HMM IDs and HMM state scores. The HMM module is configured to traverse the HMM based on the senone scores and the HMM information. Further, the interface module is configured to transfer one or more HMM scoring requests from the external computing device to the HMM module and to transfer the HMM state scores to the external computing device. | 06-26-2014 |
20150154953 | GENERATION OF WAKE-UP WORDS - A method, system and tangible computer readable medium for generating one or more wake-up words are provided. For example, the method can include receiving a text representation of the one or more wake-up words. A strength of the text representation of the one or more wake-up words can be determined based on one or more static measures. The method can also include receiving an audio representation of the one or more wake-up words. A strength of the audio representation of the one or more wake-up words can be determined based on one or more dynamic measures. Feedback on the one or more wake-up words is provided (e.g., to an end user) based on the strengths of the text and audio representations. | 06-04-2015 |
Patent application number | Description | Published |
20080201652 | Techniques for viewing and managing work items and their relationships - Various technologies and techniques are disclosed for viewing and managing work items. A work item management application is provided to allow a user to view and manage a plurality of work items from a single view. An interactive viewing feature is provided to allow the user to interactively view complex relationships between selected groups of work items. When the user selects all of the work items of a particular type in a work item group, the orphaned items are visually indicated. A many-to-many linker feature allows the user to create many-to-many relationships between a selected group of the work items in a single operation. | 08-21-2008 |
20090204912 | GENEERAL PURPOSE INFINITE DISPLAY CANVAS - Expanding and contracting a display screen container. Data is stored in a computer readable medium. The data represents a screen container such as a graphical desktop user interface displayable to a user on a computer display of a computing device. Data is stored representing artifacts, including one or more application graphical user interface artifacts for applications that are instantiated on the computing device. Information is stored specifying locations where each of the artifacts should be graphically located in the screen container. The graphical size of screen container is determined by the locations of the artifacts. Based on user input, a portion of the screen container is displayed to the user on the computer display of the computing device. The screen container may be expanded or contracted based on opening or closing graphical user interface artifacts, adding or removing artifacts, or repositioning artifacts. | 08-13-2009 |
20090322739 | Visual Interactions with Analytics - Visual interaction with an analytics-driven model view composition application. The application includes a data-model binding component that binds input data to model parameters, an analytics solver component that solves for remaining unknown model parameters, and a view composition component that generates a view composition using the model parameters. In one visual interaction, various solutions of the model are provided in alternative views of various view compositions in a single integrated composition. In another interaction, regardless of whether there are multiple view compositions illustrated in a single integrated view, there might be visual prompts in the view composition that suggest an adjustment to make that might move the value of a particular model parameter in a desired direction. | 12-31-2009 |
20120159298 | GENERATING CUSTOMIZED DATA BOUND VISUALIZATIONS - Descried herein are various technologies to visualizing data in a spreadsheet application. Customized visualizations are generated by binding a user-defined equation with a parameter of a primitive visual shape that has been selected by the user to visualized a dataset. The user-defined equation takes as input a value of data in a cell of the spreadsheet application, and the primitive visual shape is displayed to the user as a function of the output of the user-defined equation. | 06-21-2012 |
20130007671 | MULTI-FACETED RELATIONSHIP HUBS - Multi-faceted relationship hubs can support browsing an extensible set of relationship types from within a single tool window. A user can switch between relationship types within a single tool window without disrupting user flow by having to change context in a plurality of tool windows. Multiple instances of relationship hubs can be created. Browsing navigation history can be stored, allowing a user to maintain and reacquire relationship contexts. A user can preview the content of one or more files without opening the file. | 01-03-2013 |
20130074042 | VISUALIZING THREAD STATE DURING PROGRAM DEBUGGING - The present invention extends to methods, systems, and computer program products for visualizing thread state during program debugging. A tooltip can present a visual summary of the execution state of the application threads, what the values are, and patterns in the values, during debugging. As such, a developer debugging a parallel application can see the status of threads within a thread block. A visual tooltip (or other presentation mechanism) can be activated by hovering (e.g., placing a mouse pointer) over a user interface element. A visual tooltip can be presented by hovering over a status rollup visualization of the thread states or by hovering over an icon that appears in the code gutter for a code segment. Accordingly, developers can get a concise visual summary of thread states, variables, and values during debugging. | 03-21-2013 |
20130083025 | VISUAL FOCUS-BASED CONTROL OF COUPLED DISPLAYS - Various technologies described herein pertain to controlling functionality of a display based on visual focus of a user in a multiple display or multiple computational device environment. A particular display from a set of displays on which a user is visually focused is identified. The set of displays includes at least a first display and a second display. Moreover, a type of input receivable from the user via the first display and/or content rendered on the first display is controlled based on the visual focus of the user. | 04-04-2013 |
20130086105 | VOICE DIRECTED CONTEXT SENSITIVE VISUAL SEARCH - Various technologies described herein pertain to voice directed context sensitive visual searching. Visual content can be rendered on a display, and a voice directed query related to the visual content can be received. Contextual information related to the visual content can also be identified. Moreover, a search word recognized from the voice directed query and/or the contextual information can be used to detect an object from the visual content, where the object can be a part of the visual content. Further, a search can be performed using the object detected from the visual content, and a result of the search can be rendered on the display. | 04-04-2013 |
20130152051 | TIME-BASED NAVIGATION WITHIN RESOURCE UTILIZATION DATA - The present invention extends to methods, systems, and computer program products for time-based navigation within resource utilization data. A computer system is configured to present resource utilization data representing performance of computer resources. The resource utilization data is displayed on a diagnostic data trace during the execution of the application. The user can select a desired time range and the resource utilization data within the time range will be displayed at other traces. The diagnostic data trace is still presented so that the user can understand the relation between the selected time range and the overall time length. Further, the user can modify the selected time range by change the extents of the selected time range using resizing tool. The resource utilization data within the modified selected time range, similarly, is also displayed along with the diagnostic data trace. | 06-13-2013 |
20140310273 | BINDING OF DATA SOURCE TO COMPOUND CONTROL - The automated binding of a data source to a compound control. The properties of the compound control are identified. Furthermore, a particular data source is associated with the compound control. For each of one or more of the properties of the compound control, information regarding the compound control and the data source are used to identify a set of one or more fields of the particular data source that may be bound to the corresponding property of the compound control. If the corresponding property of the compound control has bound thereto an output parameter of a declarative transformation, the nature of the transformation may also be taken into consideration when identifying the set of one or more fields that may be used in order to bind to the corresponding property of the compound control. | 10-16-2014 |
20140310619 | SIGNAL CAPTURE CONTROLS IN RECALCULATION USER INTERFACE - A recalculation user interface that includes visualization controls that display in response to received data, and signal capture controls that capture corresponding environment signals upon detection of a corresponding event. A declarative transformation chain is positioned between the various controls. Examples of environmental signals captured by the signal capture controls include image, video, audio, orientation, biometrics, location, weather, or any other information about the environment. Incorporating such signal capture controls into the recalculation user interface thus allows captured environmental signals to be incorporated into the logic and other data of the transformation chain. Also, an authoring tool that permits authoring of such recalculation user interfaces is described. | 10-16-2014 |
Patent application number | Description | Published |
20080278328 | MOBILE RFID READER WITH INTEGRATED LOCATION AWARENESS FOR MATERIAL TRACKING AND MANAGEMENT - A portable RFID reader (or reader/writer) that also employs a location determination subsystem that facilitates determination of the reader (or reader/writer) location. The location subsystem can employ a satellite-based GPS (Global Positioning System) location technology where such signals are unimpeded by structures. Additionally, the location subsystem can employ other terrestrial location technologies that operate inside structures such as warehouses and the factory automation environment. | 11-13-2008 |
20090206154 | RFID ARCHITECTURE IN AN INDUSTRIAL CONTROLLER ENVIRONMENT - An RFID reader and/or writer module in an industrial controller (e.g., PLC). The RFID module interfaces internally to the controller for tight integration therewith. The RFID module can also be part of a controller communications framework and as a standalone module with the PLC as a master device, and interact with the RFID module in the same manner as it interacts with other I/O devices connected to the controller. In another aspect, RFID read/write tag technology is incorporated into some or all major PLC and rack components, and utilized for wireless communication both between PLC system components and between the PLC and other devices, locations, and media. The RFID tag can be used to store and exchange electronic keying data, security information, module diagnostics and warranty information, series and revision levels code, I/O configuration data, and, replacement data. Artificial intelligence is also employed. | 08-20-2009 |