Patents by Inventor Jason D. WILLIAMS
Jason D. WILLIAMS has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20240158398Abstract: Described herein are compounds that inhibit ALK2 and its mutants, pharmaceutical compositions including such compounds, and methods of using such compounds and compositions.Type: ApplicationFiled: April 20, 2023Publication date: May 16, 2024Inventors: Natasja Brooijmans, Jason D. Brubaker, Paul E. Fleming, Brian Lewis Hodous, Joseph L. Kim, Brett D. Williams, Douglas Wilson, Kevin J. Wilson, Mark Cronin
-
Publication number: 20240156476Abstract: Various embodiments of the systems, methods, and devices are provided for controlled operation of an intravascular lithotripsy system for breaking up calcified lesions in an anatomical conduit. More specifically, control arrangements are disclosed concerning managing and/or providing electrical energy to generate an electrical arc between a set of spaced-apart electrodes disposed within a fluid-filled member configured to contain a conductive fluid.Type: ApplicationFiled: November 10, 2023Publication date: May 16, 2024Inventors: Jason W. Staab, Austin P. Petronack, John R. Ballard, J. Samuel Batchelder, Jacob T. Williams, Donald D. Hanson, Thomas D. Brindley, Scott P. Boeshart, Jeffrey T. Moriarty
-
Publication number: 20240156477Abstract: Various embodiments of the systems, methods, and devices are provided for controlled operation of an intravascular lithotripsy system for breaking up calcified lesions in an anatomical conduit. More specifically, control arrangements are disclosed concerning managing and/or providing electrical energy to generate an electrical arc between a set of spaced-apart electrodes disposed within fluid-fillable member are disclosed.Type: ApplicationFiled: November 10, 2023Publication date: May 16, 2024Inventors: John R. Ballard, Jason W. Staab, Austin P. Petronack, J. Samuel Batchelder, Jacob T. Williams, Donald D. Hanson, Thomas D. Brindley, Scott P. Boeshart, Jeffrey T. Moriarty
-
Publication number: 20240156478Abstract: Various embodiments of the systems, methods, and devices are provided for controlled operation of an intravascular lithotripsy (“IVL”) system for breaking up calcified lesions in an anatomical conduit. More specifically, control arrangements are disclosed concerning managing and/or providing and/or assessing the electrical energy needed to generate an electrical arc between a set of spaced-apart electrodes disposed within a fluid-fillable member.Type: ApplicationFiled: November 10, 2023Publication date: May 16, 2024Inventors: John R. Ballard, Jason W. Staab, Austin P. Petronack, J. Samuel Batchelder, Jacob T. Williams, Donald D. Hanson, Thomas D. Brindley, Scott P. Boeshart, Jeffrey T. Moriarty
-
Publication number: 20240124750Abstract: A multilayer composite containing a polymeric membrane, a hot-melt adhesive layer, and a release liner, wherein the hot-melt adhesive layer comprises a thermally curable pressure-sensitive adhesive. The invention further relates to a process to make the composite and to use the composite as a roofing material, label, tape, Graphics and Medical applications.Type: ApplicationFiled: December 6, 2023Publication date: April 18, 2024Inventors: Singa D. TOBING, Jason WOLFE, Timothy KLOTS, Philip S. WILLIAMS, Hiruy YIGEZU, Sujith CHACKO
-
Patent number: 11946722Abstract: A detector for detecting the removal and/or insertion of a weapon out of and/or into a holster. The detector may transmit a message each time the weapon is removed from the holster. A recording system may receive the message and determine whether or not it will begin recording the data it captures. A detector may detect the change in a magnitude of an inductance and/or an impedance of a circuit to detect insertion and removal of the weapon into and out of the holster. The holster is configured to couple to the detector to position the detector to detect insertion and removal of the weapon. An adhesive tape may couple a detector to a holster.Type: GrantFiled: May 2, 2023Date of Patent: April 2, 2024Assignee: Axon Enterprise, Inc.Inventors: Daniel Joseph Wagner, Nache D. Shekarri, Jonathan R. Hatcher, John W. Wilson, Andrew G. Terajewicz, Lucas Kraft, Brian Piquette, Zachary B. Williams, Elliot William Weber, Jason W. Haensly
-
Publication number: 20240066330Abstract: A tool, such as a respirator, including a body, an opening defined by the body, a door coupled to the body, and a filter positioned between the body and the filter. The door actuates between open and closed positions. The filter can be removed and replaced when the door is in the open position.Type: ApplicationFiled: November 7, 2023Publication date: February 29, 2024Inventors: Aaron M. Williams, Jason D. Thurner, Grant T. Squiers
-
Patent number: 10152971Abstract: 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.Type: GrantFiled: June 23, 2016Date of Patent: December 11, 2018Assignee: NUANCE COMMUNICATIONS, INC.Inventors: Jason D. Williams, Ethan Selfridge
-
Patent number: 10108608Abstract: A dialog state tracking system. One aspect of the system is the use of multiple utterance decoders and/or multiple spoken language understanding (SLU) engines generating competing results that improve the likelihood that the correct dialog state is available to the system and provide additional features for scoring dialog state hypotheses. An additional aspect is training a SLU engine and a dialog state scorer/ranker DSR engine using different subsets from a single annotated training data set. A further aspect is training multiple SLU/DSR engine pairs from inverted subsets of the annotated training data set. Another aspect is web-style dialog state ranking based on dialog state features using discriminative models with automatically generated feature conjunctions. Yet another aspect is using multiple parameter sets with each ranking engine and averaging the rankings. Each aspect independently improves dialog state tracking accuracy and may be combined in various combinations for greater improvement.Type: GrantFiled: June 12, 2014Date of Patent: October 23, 2018Assignee: MICROSOFT TECHNOLOGY LICENSING, LLCInventors: Jason D. Williams, Geoffrey G. Zweig
-
SYSTEM AND METHOD FOR GENERATING MANUALLY DESIGNED AND AUTOMATICALLY OPTIMIZED SPOKEN DIALOG SYSTEMS
Publication number: 20170345413Abstract: 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.Type: ApplicationFiled: August 15, 2017Publication date: November 30, 2017Inventor: Jason D. Williams -
System and method for generating manually designed and automatically optimized spoken dialog systems
Patent number: 9741336Abstract: 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.Type: GrantFiled: June 17, 2016Date of Patent: August 22, 2017Assignee: Nuance Communications, Inc.Inventor: Jason D. Williams -
Publication number: 20160300572Abstract: 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.Type: ApplicationFiled: June 23, 2016Publication date: October 13, 2016Inventors: Jason D. WILLIAMS, Ethan SELFRIDGE
-
Publication number: 20160293158Abstract: 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.Type: ApplicationFiled: June 17, 2016Publication date: October 6, 2016Inventor: Jason D. Williams
-
Patent number: 9378738Abstract: 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.Type: GrantFiled: December 10, 2014Date of Patent: June 28, 2016Assignee: AT&T Intellectual Property I, L.P.Inventors: Jason D. Williams, Ethan Selfridge
-
System and method for generating manually designed and automatically optimized spoken dialog systems
Patent number: 9373323Abstract: 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.Type: GrantFiled: February 9, 2015Date of Patent: June 21, 2016Assignee: AT&T Intellectual Property I, L.P.Inventor: Jason D. Williams -
Publication number: 20150363393Abstract: A dialog state tracking system. One aspect of the system is the use of multiple utterance decoders and/or multiple spoken language understanding (SLU) engines generating competing results that improve the likelihood that the correct dialog state is available to the system and provide additional features for scoring dialog state hypotheses. An additional aspect is training a SLU engine and a dialog state scorer/ranker DSR engine using different subsets from a single annotated training data set. A further aspect is training multiple SLU/DSR engine pairs from inverted subsets of the annotated training data set. Another aspect is web-style dialog state ranking based on dialog state features using discriminative models with automatically generated feature conjunctions. Yet another aspect is using multiple parameter sets with each ranking engine and averaging the rankings. Each aspect independently improves dialog state tracking accuracy and may be combined in various combinations for greater improvement.Type: ApplicationFiled: June 12, 2014Publication date: December 17, 2015Applicant: Microsoft CorporationInventors: Jason D. Williams, Geoffrey G. Zweig
-
System and Method for Generating Manually Designed and Automatically Optimized Spoken Dialog Systems
Publication number: 20150154952Abstract: 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.Type: ApplicationFiled: February 9, 2015Publication date: June 4, 2015Inventor: Jason D. WILLIAMS -
Publication number: 20150100316Abstract: 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.Type: ApplicationFiled: December 10, 2014Publication date: April 9, 2015Inventors: Jason D. Williams, Ethan SELFRIDGE
-
System and method for generating manually designed and automatically optimized spoken dialog systems
Patent number: 8954319Abstract: 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.Type: GrantFiled: July 23, 2014Date of Patent: February 10, 2015Assignee: AT&T Intellectual Property I, L.P.Inventor: Jason D. Williams -
System and Method for Generating Manually Designed and Automatically Optimized Spoken Dialog Systems
Publication number: 20140330554Abstract: 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.Type: ApplicationFiled: July 23, 2014Publication date: November 6, 2014Inventor: Jason D. WILLIAMS