Jason Williams
Jason Williams, New York, NY US
Patent application number | Description | Published |
---|---|---|
20090030683 | SYSTEM AND METHOD FOR TRACKING DIALOGUE STATES USING PARTICLE FILTERS - Disclosed are methods, systems, and computer-readable media for tracking dialog states in a spoken dialog system. The method comprises casting a plurality of dialog states, or particles, as a network describing the probability relationships between each of a plurality of variables, sampling a subset of the plurality of dialog states, or particles, in the network, for each sampled dialog state, or particle, projecting into the future, assigning a weight to each sampled particle, and normalizing the assigned weights to yield a new estimated distribution over each variable's values, wherein the distribution over the variables is used in a spoken dialog system. Also disclosed is a method of tuning performance of the methods, systems, and computer-readable media by adding or removing particles to/from the network. | 01-29-2009 |
20090112586 | SYSTEM AND METHOD OF EVALUATING USER SIMULATIONS IN A SPOKEN DIALOG SYSTEM WITH A DIVERSION METRIC - Systems, methods and computer-readable media associated with using a divergence metric to evaluate user simulations in a spoken dialog system. The method employs user simulations of a spoken dialog system and includes aggregating a first set of one or more scores from a real user dialog, aggregating a second set of one or more scores from a simulated user dialog associated with a user model, determining a similarity of distributions associated with each of the first set and the second set, wherein the similarity is determined using a divergence metric that does not require any assumptions regarding a shape of the distributions. It is preferable to use a Cramér-von Mises divergence. | 04-30-2009 |
20090112598 | SYSTEM AND METHOD FOR APPLYING PROBABILITY DISTRIBUTION MODELS TO DIALOG SYSTEMS IN THE TROUBLESHOOTING DOMAIN - Disclosed herein are systems, methods, and computer-readable media for troubleshooting based on a probability distribution model. The method for troubleshooting based on a probability distribution model includes establishing a speech-based channel of interaction, establishing at least one non-speech-based channel of interaction, maintaining a probability distribution over time for each of a plurality of component variables describing the state of the product or service and state of the conversation, and troubleshooting a product or service by responding based on the probability distribution. | 04-30-2009 |
20100138215 | SYSTEM AND METHOD FOR USING ALTERNATE RECOGNITION HYPOTHESES TO IMPROVE WHOLE-DIALOG UNDERSTANDING ACCURACY - Disclosed herein are systems, computer-implemented methods, and tangible computer-readable media for using alternate recognition hypotheses to improve whole-dialog understanding accuracy. The method includes receiving an utterance as part of a user dialog, generating an N-best list of recognition hypotheses for the user dialog turn, selecting an underlying user intention based on a belief distribution across the generated N-best list and at least one contextually similar N-best list, and responding to the user based on the selected underlying user intention. Selecting an intention can further be based on confidence scores associated with recognition hypotheses in the generated N-best lists, and also on the probability of a user's action given their underlying intention. A belief or cumulative confidence score can be assigned to each inferred user intention. | 06-03-2010 |
20110010164 | SYSTEM AND METHOD FOR GENERATING MANUALLY DESIGNED AND AUTOMATICALLY OPTIMIZED SPOKEN DIALOG SYSTEMS - Disclosed herein are systems, computer-implemented methods, and tangible computer-readable storage media for generating a natural language spoken dialog system. The method includes nominating a set of allowed dialog actions and a set of contextual features at each turn in a dialog, and selecting an optimal action from the set of nominated allowed dialog actions using a machine learning algorithm. The method includes generating a response based on the selected optimal action at each turn in the dialog. The set of manually nominated allowed dialog actions can incorporate a set of business rules. Prompt wordings in the generated natural language spoken dialog system can be tailored to a current context while following the set of business rules. A compression label can represent at least one of the manually nominated allowed dialog actions. | 01-13-2011 |
20110054893 | SYSTEM AND METHOD FOR GENERATING USER MODELS FROM TRANSCRIBED DIALOGS - Disclosed herein are systems, computer-implemented methods, and computer-readable storage media for generating personalized user models. The method includes receiving automatic speech recognition (ASR) output of speech interactions with a user, receiving an ASR transcription error model characterizing how ASR transcription errors are made, generating guesses of a true transcription and a user model via an expectation maximization (EM) algorithm based on the error model and the respective ASR output where the guesses will converge to a personalized user model which maximizes the likelihood of the ASR output. The ASR output can be unlabeled. The method can include casting speech interactions as a dynamic Bayesian network with four variables: (s), (u), (r), (m), and encoding relationships between (s), (u), (r), (m) as conditional probability tables. At each dialog turn (r) and (m) are known and (s) and (u) are hidden. | 03-03-2011 |
20110099012 | SYSTEM AND METHOD FOR ESTIMATING THE RELIABILITY OF ALTERNATE SPEECH RECOGNITION HYPOTHESES IN REAL TIME - Disclosed herein are systems, methods, and computer-readable storage media for estimating reliability of alternate speech recognition hypotheses. A system configured to practice the method receives an N-best list of speech recognition hypotheses and features describing the N-best list, determines a first probability of correctness for each hypothesis in the N-best list based on the received features, determines a second probability that the N-best list does not contain a correct hypothesis, and uses the first probability and the second probability in a spoken dialog. The features can describe properties of at least one of a lattice, a word confusion network, and a garbage model. In one aspect, the N-best lists are not reordered according to reranking scores. The determination of the first probability of correctness can include a first stage of training a probabilistic model and a second stage of distributing mass over items in a tail of the N-best list. | 04-28-2011 |
20110131048 | SYSTEM AND METHOD FOR AUTOMATICALLY GENERATING A DIALOG MANAGER - Disclosed herein are systems, methods, and computer-readable storage media for automatically generating a dialog manager for use in a spoken dialog system. A system practicing the method receives a set of user interactions having features, identifies an initial policy, evaluates all of the features in a linear evaluation step of the algorithm to identify a set of most important features, performs a cubic policy improvement step on the identified set of most important features, repeats the previous two steps one or more times, and generates a dialog manager for use in a spoken dialog system based on the resulting policy and/or set of most important features. Evaluating all of the features can include estimating a weight for each feature which indicates how much each feature contributes to at least one of the identified policies. The system can ignore features not in the set of most important features. | 06-02-2011 |
20110137654 | SYSTEM AND METHOD FOR EFFICIENT TRACKING OF MULTIPLE DIALOG STATES WITH INCREMENTAL RECOMBINATION - Disclosed herein are systems, methods, and computer-readable storage media for tracking multiple dialog states. A system practicing the method receives an N-best list of speech recognition candidates, a list of current partitions, and a belief for each of the current partitions. A partition is a group of dialog states. In an outer loop, the system iterates over the N-best list of speech recognition candidates. In an inner loop, the system performs a split, update, and recombination process to generate a fixed number of partitions after each speech recognition candidate in the N-best list. The system recognizes speech based on the N-best list and the fixed number of partitions. The split process can perform all possible splits on all partitions. The update process can compute an estimated new belief. The estimated new belief can be a product of ASR reliability, user likelihood to produce this action, and an original belief. | 06-09-2011 |
20120179467 | USER INTENTION BASED ON N-BEST LIST OF RECOGNITION HYPOTHESES FOR UTTERANCES IN A DIALOG - Disclosed herein are systems, computer-implemented methods, and tangible computer-readable media for using alternate recognition hypotheses to improve whole-dialog understanding accuracy. The method includes receiving an utterance as part of a user dialog, generating an N-best list of recognition hypotheses for the user dialog turn, selecting an underlying user intention based on a belief distribution across the generated N-best list and at least one contextually similar N-best list, and responding to the user based on the selected underlying user intention. Selecting an intention can further be based on confidence scores associated with recognition hypotheses in the generated N-best lists, and also on the probability of a user's action given their underlying intention. A belief or cumulative confidence score can be assigned to each inferred user intention. | 07-12-2012 |
20130060570 | SYSTEM AND METHOD FOR ADVANCED TURN-TAKING FOR INTERACTIVE SPOKEN DIALOG SYSTEMS - Disclosed herein are systems, methods, and non-transitory computer-readable storage media for advanced turn-taking in an interactive spoken dialog system. A system configured according to this disclosure can incrementally process speech prior to completion of the speech utterance, and can communicate partial speech recognition results upon finding particular conditions. A first condition which, if found, allows the system to communicate partial speech recognition results, is that the most recent word found in the partial results is statistically likely to be the termination of the utterance, also known as a terminal node. A second condition is the determination that all search paths within a speech lattice converge to a common node, also known as a pinch node, before branching out again. Upon finding either condition, the system can communicate the partial speech recognition results. Stability and correctness probabilities can also determine which partial results are communicated. | 03-07-2013 |
20130132080 | SYSTEM AND METHOD FOR CROWD-SOURCED DATA LABELING - Disclosed herein are systems, methods, and non-transitory computer-readable storage media for crowd-sourced data labeling. The system requests a respective response from each of a set of entities. The set of entities includes crowd workers. Next, the system incrementally receives a number of responses from the set of entities until at least one of an accuracy threshold is reached and m responses are received, wherein the accuracy threshold is based on characteristics of the number of responses. Finally, the system generates an output response based on the number of responses. | 05-23-2013 |
20130289985 | System and Method for Generating User Models From Transcribed Dialogs - Disclosed herein are systems, computer-implemented methods, and computer-readable storage media for generating personalized user models. The method includes receiving automatic speech recognition (ASR) output of speech interactions with a user, receiving an ASR transcription error model characterizing how ASR transcription errors are made, generating guesses of a true transcription and a user model via an expectation maximization (EM) algorithm based on the error model and the respective ASR output where the guesses will converge to a personalized user model which maximizes the likelihood of the ASR output. The ASR output can be unlabeled. The method can include casting speech interactions as a dynamic Bayesian network with four variables: (s), (u), (r), (m), and encoding relationships between (s), (u), (r), (m) as conditional probability tables. At each dialog turn (r) and (m) are known and (s) and (u) are hidden. | 10-31-2013 |
Jason Williams, Ann Arbor, MI US
Patent application number | Description | Published |
---|---|---|
20090177432 | APPARATUS AND METHOD FOR REAL TIME MEASUREMENT OF SUBSTRATE TEMPERATURES FOR USE IN SEMICONDUCTOR GROWTH AND WAFER PROCESSING - The invention is an optical method and apparatus for measuring the temperature of semiconductor substrates in real-time, during thin film growth and wafer processing. Utilizing the nearly linear dependence of the interband optical absorption edge on temperature, the present method and apparatus result in highly accurate measurement of the absorption edge in diffuse reflectance and transmission geometry, in real time, with sufficient accuracy and sensitivity to enable closed loop temperature control of wafers during film growth and processing. The apparatus operates across a wide range of temperatures covering all of the required range for common semiconductor substrates. | 07-09-2009 |
20100274523 | APPARATUS AND METHOD FOR REAL TIME MEASUREMENT OF SUBSTRATE TEMPERATURES FOR USE IN SEMICONDUCTOR GROWTH AND WAFER PROCESSING - The invention is an optical method and apparatus for measuring the temperature of semiconductor substrates in real-time, during thin film growth and wafer processing. Utilizing the nearly linear dependence of the interband optical absorption edge on temperature, the present method and apparatus result in highly accurate measurement of the absorption edge in diffuse reflectance and transmission geometry, in real time, with sufficient accuracy and sensitivity to enable closed loop temperature control of wafers during film growth and processing. The apparatus operates across a wide range of temperatures covering all of the required range for common semiconductor substrates. | 10-28-2010 |
Jason Williams, Queen Creek, AZ US
Patent application number | Description | Published |
---|---|---|
20130043328 | Thermal protector for a sprinkler head - One embodiment will protect the sprinkler head | 02-21-2013 |
Jason Williams, South San Francisco, CA US
Patent application number | Description | Published |
---|---|---|
20130064826 | ANTI-EMR1 ANTIBODIES - The invention provides anti-EMR1 antibodies and methods of using such antibodies to treat EMR1-related diseases. | 03-14-2013 |
Jason Williams, Fairhaven, MA US
Patent application number | Description | Published |
---|---|---|
20130252760 | COLOR GOLF BALL - The present invention is directed to a golf ball comprising a core, a cover and optionally an intermediate layer disposed between the core and the cover which in any combination comprise at least two color contributing components, each of which comprises a colorant that contributes to an overall golf ball color, the color contributing components having substantially similar hues and different saturations, wherein the hue and saturation and a chroma of each contributing component contributes to an overall golf ball hue, saturation and chroma such that: the overall golf ball hue is substantially similar to the hue of each color contributing component; the overall golf ball saturation is different than the saturation of at least one of the color contributing components; and the overall golf ball chroma is different than the chroma of at least one of the color contributing components. | 09-26-2013 |
20130252764 | COLOR GOLF BALL - A golf ball comprising: a core comprising at least one layer A, a cover comprising at least one layer B, an intermediate layer C disposed between the core and the cover, and a coating D applied on an outermost surface of the golf ball. At least two of layer A, layer B, layer C and coating D comprise a golf ball color contributing component comprising a color and contributing to an overall golf ball color, wherein at least two golf ball color contributing components have different saturations. The overall golf ball hue is substantially similar to the hue of each color contributing component; the overall golf ball saturation is different than the saturation of at least one color contributing component and the overall golf ball chroma is different than the chroma of at least one color contributing component. | 09-26-2013 |
Jason Williams, Nisku CA
Patent application number | Description | Published |
---|---|---|
20130288810 | Universal Joint for a Downhole Drilling Motor - A universal joint carried by an elongate body having an axis. The universal joint has an inner race that pivots omni-directionally within an outer race and a series of first and second opposed cavities formed in the inner race and the outer race. There are a plurality of torque transfer elements, each torque transfer element having a first portion that engages a first cavity and a second portion that engages a corresponding second cavity. The first cavity is a socket that permits rotation of the first portion within the first cavity as the inner race pivots omni-directionally within the outer race and the second cavity is a track oriented in the direction of the axis of the elongate body. The second portion moves along the track as the inner race pivots omni-directionally within the outer race of the second portion along the track. The second portion has at least one drive surface that engages an inner surface of the track at more than one point along the direction of the track. | 10-31-2013 |
Jason Williams, Seattle, WA US
Patent application number | Description | Published |
---|---|---|
20130268274 | System and Method for Efficient Tracking of Multiple Dialog States with Incremental Recombination - Disclosed herein are systems, methods, and computer-readable storage media for tracking multiple dialog states. A system practicing the method receives an N-best list of speech recognition candidates, a list of current partitions, and a belief for each of the current partitions. A partition is a group of dialog states. In an outer loop, the system iterates over the N-best list of speech recognition candidates. In an inner loop, the system performs a split, update, and recombination process to generate a fixed number of partitions after each speech recognition candidate in the N-best list. The system recognizes speech based on the N-best list and the fixed number of partitions. The split process can perform all possible splits on all partitions. The update process can compute an estimated new belief. The estimated new belief can be a product of ASR reliability, user likelihood to produce this action, and an original belief. | 10-10-2013 |
20140156268 | INCREMENTAL SPEECH RECOGNITION FOR DIALOG SYSTEMS - A system and method for integrating incremental speech recognition in dialog systems. An example system configured to practice the method receives incremental speech recognition results of user speech as part of a dialog with a user, and copies a dialog manager operating on the user speech to generate temporary instances of the dialog manager. Then the system evaluates actions the temporary instances of the dialog manager would take based on the incremental speech recognition results, and identifies an action that would advance the dialog and a corresponding temporary instance of the dialog manager. The system can then execute the action in the dialog and optionally replace the dialog manager with the corresponding temporary instance of the dialog manager. The action can include making a turn-taking decision in the dialog, such as whether, what, and when to speak or whether to be silent. | 06-05-2014 |
Jason Williams, Gulf Shores, AL US
Patent application number | Description | Published |
---|---|---|
20140234275 | METHOD FOR TREATING ALS VIA THE INCREASED PRODUCTION OF FACTOR H - Methods and systems for the treatment for ALS incorporating stem cells harvested from the subject to be treated. These stem cells may be genetically altered with the addition of several genes of interest. Then, the patient will receive systemic gene therapy for the muscles and directed specifically at motor neurons. In this multi-pronged treatment approach, the stem cells provide immune regulation and the regeneration of motor neurons. And, the new motor neurons carry the added genes, which are protective against motor neuron death from ALS. The systemic therapy increases the amount of genes, which further reduces the effects of ALS. Additional gene therapy administered in the muscle will be further protective of the axon, while maintaining muscle mass and function. | 08-21-2014 |
Jason Williams, Menlo Park, CA US
Patent application number | Description | Published |
---|---|---|
20140258460 | Methods and Systems for Offline Execution of Rich Internet Applications - Methods for offline execution of Rich Internet Applications are disclosed. In one embodiment, the method includes receiving at a remote destination a client value of a Rich Internet Application (RIA) information for an RIA from a client, wherein the RIA information is stored and modified on the client before being received by the remote destination. The method further includes determining if the client value is to replace a remote destination value of the RIA information stored on the remote destination. The method further includes replacing the remote destination value with the client value to synchronize the RIA information between the client and the remote destination when it is determined that the client value is to replace the remote destination value. | 09-11-2014 |
Jason Williams, Santa Clara, CA US
Patent application number | Description | Published |
---|---|---|
20140308031 | WEARABLE CAMERA - A garment clip is disclosed. The garment clip houses a camera and comprising a first portion housing operational circuitry and a second portion supporting an image capture component. The second portion has a mass which is less than the first portion. The first and second portions are connected in a configuration such that, when the clip is secured to the garment, the image capture component faces outwardly and the first portion is at least partially concealed by the garment. | 10-16-2014 |
20140320687 | CAMERA TAP SWITCH - Various embodiments provide a wearable camera that can be worn by a user. The wearable camera includes an accelerometer that can be used to detect camera motion. Input can be provided to the camera in the form of one or more taps which have an associated motion profile, as sensed by the accelerometer. The tap or taps can be mapped to camera functionality to activate the functionality. | 10-30-2014 |
20140333828 | PORTABLE CAMERA DOCK - A portable camera dock is configured to receive a camera and enable data to be transferred between the camera and another device connected to the portable camera dock. The portable camera dock can also enable the camera to be recharged. Further, the portable camera dock can include mounting structure to enable the portable camera dock to be mounted to other structures to facilitate portability of a camera docked to the camera dock. | 11-13-2014 |
Jason Williams, Bristol, CT US
Patent application number | Description | Published |
---|---|---|
20140339325 | DOUBLE BEND STRAW - A double bend straw comprising: a first segment at a top portion of the double bend straw; a second segment in a middle portion of the double bend straw; a third segment at a bottom portion of the double bend straw; a first accordion portion connecting the first segment to the second segment; and a second accordion portion connecting the second segment to the third segment, wherein the first accordion portion and the second accordion portion enable the double bend straw to extend, retract and bend as desired by a user. The first segment includes either an opening or a mouthpiece at a top end of the first segment. | 11-20-2014 |
Jason Williams, Greer, SC US
Patent application number | Description | Published |
---|---|---|
20150046578 | MOBILE TROUBLE TICKET - A device is configured to determine that the device is experiencing a problem, and to determine a problem type associated with the problem. The device is configured to determine a set of questions, based on the problem type, and to provide the set of questions to a user of the device. The device is configured to receive user input including responses to the set of questions. The device is configured to determine device information associated with one or more hardware components, hardware attributes, or software attributes associated with the user device. The device is configured to generate a trouble ticket based on the set of questions, the user input and the device information, and to transmit the trouble ticket. | 02-12-2015 |
Jason Williams, Dearborn Heights, MI US
Patent application number | Description | Published |
---|---|---|
20150114346 | METHODS AND SYSTEMS FOR ADJUSTING ENGINE AIRFLOW BASED ON OUTPUT FROM AN OXYGEN SENSOR - Methods and systems are provided for adjusting a throttle based on an intake oxygen sensor output. In one example, a method may include adjusting a position of a throttle based on a dilution threshold and a total aircharge dilution level, the total dilution aircharge level based on an output of an intake oxygen sensor. Additionally, spark timing may be adjusted based on the total aircharge dilution level. | 04-30-2015 |
Jason Williams, Redwood City, CA US
Patent application number | Description | Published |
---|---|---|
20150203578 | ANTI-SIGLEC-8 ANTIBODIES AND METHODS OF USE THEREOF - The invention provides humanized anti-Siglec-8 antibodies and their use in treating and preventing eosinophil-mediated disorders and/or mast cell-mediated disorders, as well as compositions and kits comprising the humanized anti-Siglec-8 antibodies. | 07-23-2015 |