Patent application number | Description | Published |
20120173240 | Subspace Speech Adaptation - Subspace speech adaptation may be utilized for facilitating the recognition of speech containing short utterances. Speech training data may be received in a speech model by a computer. A first matrix may be determined for preconditioning speech statistics based on the speech training data. A second matrix may be determined for representing a basis for the speech to be recognized. A set of basis matrices may then be determined from the first matrix and the second matrix. Speech test data including a short utterance may then be received by the computer. The computer may then apply the set of basis matrices to the speech test data to produce a transcription. The transcription may represent speech recognition of the short utterance. | 07-05-2012 |
20140214420 | FEATURE SPACE TRANSFORMATION FOR PERSONALIZATION USING GENERALIZED I-VECTOR CLUSTERING - Personalization for Automatic Speech Recognition (ASR) is associated with a particular device. A generalized i-vector clustering method is used to train i-vector parameters on utterances received from a device and to classify test utterances from the same device. A sub-loading matrix and a residual noise term may be used when determining the personalization. A Universal Background Model (UBM) is trained using the utterances. The UBM is applied to obtain i-vectors of training utterances received from a device and a Gaussian Mixture Model (GMM) is trained using the i-vectors. During testing, the i-vector for each utterance received from the device is estimated using the device's UBM. The utterance is then assigned to the cluster with the closest centroid in the GMM. For each utterance, the i-vector and the residual noise estimation is performed. Hyperparameter estimation is also performed. The i-vector estimation and hyperparameter estimation are performed until convergence. | 07-31-2014 |
20140257803 | CONSERVATIVELY ADAPTING A DEEP NEURAL NETWORK IN A RECOGNITION SYSTEM - Various technologies described herein pertain to conservatively adapting a deep neural network (DNN) in a recognition system for a particular user or context. A DNN is employed to output a probability distribution over models of context-dependent units responsive to receipt of captured user input. The DNN is adapted for a particular user based upon the captured user input, wherein the adaption is undertaken conservatively such that a deviation between outputs of the adapted DNN and the unadapted DNN is constrained. | 09-11-2014 |
20150066496 | ASSIGNMENT OF SEMANTIC LABELS TO A SEQUENCE OF WORDS USING NEURAL NETWORK ARCHITECTURES - Technologies pertaining to slot filling are described herein. A deep neural network, a recurrent neural network, and/or a spatio-temporally deep neural network are configured to assign labels to words in a word sequence set forth in natural language. At least one label is a semantic label that is assigned to at least one word in the word sequence. | 03-05-2015 |
20150161101 | RECURRENT CONDITIONAL RANDOM FIELDS - Recurrent conditional random field (R-CRF) embodiments are described. In one embodiment, the R-CFR receives feature values corresponding to a sequence of words. Semantic labels for words in the sequence of words are then generated and each label is assigned to the appropriate one of the words in the sequence of words. The R-CRF used to accomplish these tasks includes a recurrent neural network (RNN) portion and a conditional random field (CRF) portion. The RNN portion receives feature values associated with a word in the sequence of words and outputs RNN activation layer activations data that is indicative of a semantic label. The CRF portion inputs the RNN activation layer activations data output from the RNN for one or more words in the sequence of words and outputs label data that is indicative of a separate semantic label that is to be assigned to each of the words. | 06-11-2015 |
20150364127 | ADVANCED RECURRENT NEURAL NETWORK BASED LETTER-TO-SOUND - The technology relates to performing letter-to-sound conversion utilizing recurrent neural networks (RNNs). The RNNs may be implemented as RNN modules for letter-to-sound conversion. The RNN modules receive text input and convert the text to corresponding phonemes. In determining the corresponding phonemes, the RNN modules may analyze the letters of the text and the letters surrounding the text being analyzed. The RNN modules may also analyze the letters of the text in reverse order. The RNN modules may also receive contextual information about the input text. The letter-to-sound conversion may then also be based on the contextual information that is received. The determined phonemes may be utilized to generate synthesized speech from the input text. | 12-17-2015 |
20150364128 | HYPER-STRUCTURE RECURRENT NEURAL NETWORKS FOR TEXT-TO-SPEECH - The technology relates to converting text to speech utilizing recurrent neural networks (RNNs). The recurrent neural networks may be implemented as multiple modules for determining properties of the text. In embodiments, a part-of-speech RNN module, letter-to-sound RNN module, a linguistic prosody tagger RNN module, and a context awareness and semantic mining RNN module may all be utilized. The properties from the RNN modules are processed by a hyper-structure RNN module that determine the phonetic properties of the input text based on the outputs of the other RNN modules. The hyper-structure RNN module may generate a generation sequence that is capable of being converting to audible speech by a speech synthesizer. The generation sequence may also be optimized by a global optimization module prior to being synthesized into audible speech. | 12-17-2015 |
20160091965 | NATURAL MOTION-BASED CONTROL VIA WEARABLE AND MOBILE DEVICES - A “Natural Motion Controller” identifies various motions of one or more parts of a user's body to interact with electronic devices, thereby enabling various natural user interface (NUI) scenarios. The Natural Motion Controller constructs composite motion recognition windows by concatenating an adjustable number of sequential periods of inertial sensor data received from a plurality of separate sets of inertial sensors. Each of these separate sets of inertial sensors are coupled to, or otherwise provide sensor data relating to, a separate user worn, carried, or held mobile computing device. Each composite motion recognition window is then passed to a motion recognition model trained by one or more machine-based deep learning processes. This motion recognition model is then applied to the composite motion recognition windows to identify a sequence of one or more predefined motions. Identified motions are then used as the basis for triggering execution of one or more application commands. | 03-31-2016 |
Patent application number | Description | Published |
20090105592 | MULTI-STAGE DIGITAL ULTRASOUND BEAMFORMER - Elements in an ultrasound array are activated according to a transmit beamformer to create a series of transmit beams. For each transmit beam, the first stage of a receive beamformer determines a plurality of primary receive beams. A second beamformer stage then computes secondary receive beams as a function of the primary receive beams that correspond to return signals from different transmit beams to a common receive beam origin. For example, each secondary receive beam may be calculated as a function of the weighted, time-delayed sum of the primary receive beams. At least one of the secondary receive beams is then output from the beamformer to be used in creating a displayed image. | 04-23-2009 |
20090192387 | CONTINUOUS ACQUISITION AND PROCESSING OF ULTRASOUND COLOR DATA - A method displays ultrasound color flow image data in a plurality of output frames by continuously acquiring color flow image data. Each output frame includes a plurality of scan lines that collectively represent a field of view for an ultrasound image. The method includes sequentially transmitting a plurality of ultrasound beams. For each of the transmitted beams, multiple receive beams are formed along respective parallel scan lines. As the sequence progresses, sets of co-linear receive beams are formed along each of the respective scan lines at a predetermined rate both within a particular frame and between successive frames. The method also includes processing the sets of co-linear receive beams along each of the respective scan lines to generate color flow image data corresponding to the respective scan lines, and displaying a color flow image representing the generated color flow image data. | 07-30-2009 |
20110066030 | SYSTEMS AND METHODS FOR SHEAR WAVE FIELD FORMATION - An ultrasound imaging system provides dynamic control of a shear wave front used to image viscoelasticity in a biological tissue. The system receives an indication of a region of interest and selects a shear wave front shape. The system also selects, based on the selected shear wave front shape, focus locations for a plurality of push pulses and a sequence for moving a shear wave source among the focus locations. The system transmits a series of push pulses according to the selected sequence, and determines a speed of the shear wave front as it passes through the region of interest. Changes in the speed of the shear wave front are related to changes in stiffness within the tissue. | 03-17-2011 |
20120152021 | METHODS AND SYSTEMS FOR ULTRASONIC IMAGING - A method for ultrasonic imaging comprises: emitting Doppler pulses to a target to be detected; performing a Doppler scan with Doppler pulses; receiving echo signals from the target, wherein the echo signals include Doppler pulse echo signals; processing the echo signals, wherein processing comprises an imaging step, the imaging step comprising parallel processing steps including a 2D image processing step, a flow image processing step, and a spectrum image processing step, wherein the 2D image processing step is configured for processing the echo signals to obtain 2D image signals, the flow image processing step is configured for processing the echo signals to obtain flow image signals, and the spectrum image processing step is configured for processing the echo signals to obtain spectrum image signals; and displaying the processed echo signals. | 06-21-2012 |
Patent application number | Description | Published |
20120246270 | SELECTIVELY ENABLED QUALITY OF SERVICE POLICY - A computer system that implements a quality of service policy. Information defining the quality of service policy is stored in a central location, such as a server within an enterprise. Policy management software on clients in the network download quality of service policy information from the central location to the clients. Within a client, a portion of the policy information is selected based on its applicability to a particular connection. The selected information is cached with an association to the connection so that, as datagrams are generated for transmission over the network, relevant policy information is quickly accessed for use in controlling transmission characteristics of datagrams sent using that connection. The policy information is applied on a datagram-by-datagram basis, allowing policy information to be selectively applied based on network type. Policy information may be selectively applied to those datagrams transmitted over a managed network. | 09-27-2012 |
20130006952 | ORGANIZING SEARCH HISTORY INTO COLLECTIONS - Computer-storage media, methods, and systems for improving the ability of a user to accomplish a task that is pending during a search session are provided. This pending task can be distilled by identifying a current searching intent associated with a recently submitted query and by determining which candidate tasks are most comparable to the current searching intent of a user. The candidate tasks are mined from a search history of the user by categorizing those navigation events that appear to share a semantically common concept. Upon performing a comparison, the candidate task that captures the user's true current searching intent is designated as the pending task. When a user invokes the pending task, a collection of elements that are associated with the pending task are dynamically organized into a sharable content page, thereby providing a collaborative experience that involves exposing the collection to contacts and accepting feedback therefrom. | 01-03-2013 |
20130282688 | ORGANIZING SEARCH HISTORY INTO COLLECTIONS - Computer-storage media, methods, and systems for improving the ability of a user to accomplish a task that is pending during a search session are provided. When a user invokes the pending task, a collection of elements that are associated with the pending task are dynamically organized into a sharable content page that may be shared with a user's contacts via a social network. The user's contacts may comment on or provide feedback related to the pending task. The feedback may be published to the sharable content page and presented to the user on a user interface. | 10-24-2013 |
20150193542 | RESULT PROMINENCE IN SEARCH - Architecture that computes a definitive answer to a user's top intent of a search query, and positions the top intent answer in a prominent way and at a prominent location of a results page or other search user interface, where the user is most likely to see the top intent answer in an expeditious manner. This may be at the top-most position of the page, above the search results and advertisements, but below the page header and search box. Additionally, the definitive and prominently-placed answer can be presented with an interactive, animated, and/or visually rich element that supplements the original intent. The top intent location can be the boldest element on the page, extend at least one full dimension of the page, use larger fonts and bolder colors than the rest of the search results, and which makes finding the answer easier and faster for the user to locate. | 07-09-2015 |
Patent application number | Description | Published |
20080219985 | PROK2 ANTAGONISTS AND METHODS OF USE - The present invention provides methods of using PROK2 and PROK1 antagonist, including monoclonal antibodies to treat inflammation, angiogenesis, and cancer. | 09-11-2008 |
20100221244 | ANTAGONIZING SIGNAL TRANSDUCTION IN DORSAL ROOT GANGLION CELLS IN A SUBJECT WITH IL-31 ANTAGONISTS - Use of antagonists to IL-31 are used to treat inflammation and pain by inhibiting, preventing, reducing, minimizing, limiting or minimizing stimulation in neuronal tissues. Such antagonists include antibodies and fragments, derivative, or variants thereof. Symptoms such as pain, tingle, sensitization, tickle associated with neuropathies are ameliorated. | 09-02-2010 |
20100297125 | METHODS OF TREATING PAIN USING ANTAGONISTS OF IL-31, IL-31RA AND/OR OSMRB - Use of antagonists to IL-31Ra and OSMRb are used to treat inflammation and pain by inhibiting, preventing, reducing, minimizing, limiting or minimizing stimulation in neuronal tissues. Such antagonists include soluble receptors, antibodies and fragments, derivative, or variants thereof. Symptoms such as pain, tingle, sensitization, tickle associated with neuropathies are ameliorated. | 11-25-2010 |
20110076206 | Reagent containers for compact test devices - Embodiments disclosed herein relate to reagent containers configured to allow for different liquid and solid reagents to be mixed in situ prior to the measurement. | 03-31-2011 |
20110177072 | METHODS OF TREATING INFLAMMATION IN NEURONAL TISSUE - Use of antagonists to IL-31 are used to treat inflammation and pain by inhibiting, preventing, reducing, minimizing, limiting or minimizing stimulation in neuronal tissues. Such antagonists include antibodies and fragments, derivative, or variants thereof. Symptoms such as pain, tingle, sensitization, tickle associated with neuropathies are ameliorated. | 07-21-2011 |
20110177074 | COMPOSITIONS AND METHODS FOR INHIBITING PDGFRBETA AND VEGF-A - Disclosed are antagonists of PDGF receptor β (PDGFRβ) and VEGF-A, including neutralizing anti-PDGFRβ and anti-VEGF-A antibodies, as well as related compositions and methods. Anti-PDGFRβ and anti-VEGF-A antibodies disclosed herein include bispecific antibodies capable of binding and neutralizing both PDGFRβ and VEGF-A. Also disclosed are methods of treating an neovascular disorder, such as cancer or an neovascular ocular disorder, using a PDGFRβ and/or VEGF-A antagonist. | 07-21-2011 |
20110177086 | METHODS OF ANTAGONIZING SIGNAL TRANSDUCTION IN DORSAL ROOT GANGLION CELLS - Use of antagonists to IL-31Ra and OSMRb are used to treat inflammation and pain by inhibiting, preventing, reducing, minimizing, limiting or minimizing stimulation in neuronal tissues. Such antagonists include soluble receptors, antibodies and fragments, derivative, or variants thereof. Symptoms such as pain, tingle, sensitization, tickle associated with neuropathies are ameliorated. | 07-21-2011 |
20120107310 | METHODS OF ANTAGONIZING SIGNAL TRANSDUCTION IN SPINAL CORD CELLS - Use of antagonists to IL-31 are used to treat inflammation and pain by inhibiting, preventing, reducing, minimizing, limiting or minimizing stimulation in neuronal tissues. Such antagonists include antibodies and fragments, derivative, or variants thereof. Symptoms such as pain, tingle, sensitization, tickle associated with neuropathies are ameliorated. | 05-03-2012 |
20120207757 | METHODS OF ANTAGONIZING SIGNAL TRANSDUCTION IN SPINAL CORD CELLS - Use of antagonists to IL-31Ra and OSMRb are used to treat inflammation and pain by inhibiting, preventing, reducing, minimizing, limiting or minimizing stimulation in neuronal tissues. Such antagonists include soluble receptors, antibodies and fragments, derivative, or variants thereof. Symptoms such as pain, tingle, sensitization, tickle associated with neuropathies are ameliorated. | 08-16-2012 |
20130177562 | METHODS OF ANTAGONIZING SIGNAL TRANSDUCTION IN DORSAL ROOT GANGLION CELLS - Use of antagonists to IL-31 are used to treat inflammation and pain by inhibiting, preventing, reducing, minimizing, limiting or minimizing stimulation in neuronal tissues. Such antagonists include antibodies and fragments, derivative, or variants thereof. Symptoms such as pain, tingle, sensitization, tickle associated with neuropathies are ameliorated. | 07-11-2013 |
20130195855 | METHODS OF ANTAGONIZING SIGNAL TRANSDUCTION IN DORSAL ROOT GANGLION CELLS - Use of antagonists to IL-31Ra and OSMRb are used to treat inflammation and pain by inhibiting, preventing, reducing, minimizing, limiting or minimizing stimulation in neuronal tissues. Such antagonists include soluble receptors, antibodies and fragments, derivative, or variants thereof. Symptoms such as pain, tingle, sensitization, tickle associated with neuropathies are ameliorated. | 08-01-2013 |
20140127206 | METHODS OF TREATING PAIN USING AN IL-31 MONOCLONAL ANTIBODY - Use of antagonists to IL-31 are used to treat inflammation and pain by inhibiting, preventing, reducing, minimizing, limiting or minimizing stimulation in neuronal tissues. Such antagonists include antibodies and fragments, derivative, or variants thereof. Symptoms such as pain, tingle, sensitization, tickle associated with neuropathies are ameliorated. | 05-08-2014 |
20140186346 | METHODS OF TREATING PAIN USING AN IL-31RA OR OSMR-B ANTAGONIST - Use of antagonists to IL-31Ra and OSMRb are used to treat inflammation and pain by inhibiting, preventing, reducing, minimizing, limiting or minimizing stimulation in neuronal tissues. Such antagonists include soluble receptors, antibodies and fragments, derivative, or variants thereof. Symptoms such as pain, tingle, sensitization, tickle associated with neuropathies are ameliorated. | 07-03-2014 |
20150132299 | METHODS OF TREATING NEURONAL INFLAMMATION USING AN IL-31 MONOCLONAL ANTIBODY - Use of antagonists to IL-31 are used to treat inflammation and pain by inhibiting, preventing, reducing, minimizing, limiting or minimizing stimulation in neuronal tissues. Such antagonists include antibodies and fragments, derivative, or variants thereof. Symptoms such as pain, tingle, sensitization, tickle associated with neuropathies are ameliorated. | 05-14-2015 |
20150132300 | METHODS OF ANTAGONIZING SIGNAL TRANSDUCTION IN SPINAL CORD CELLS USING AN IL-31RA OR OSMR-B ANTAGONIST - Use of antagonists to IL-31Ra and OSMRb are used to treat inflammation and pain by inhibiting, preventing, reducing, minimizing, limiting or minimizing stimulation in neuronal tissues. Such antagonists include soluble receptors, antibodies and fragments, derivative, or variants thereof. Symptoms such as pain, tingle, sensitization, tickle associated with neuropathies are ameliorated. | 05-14-2015 |