Patents by Inventor Barnaby James
Barnaby James 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).
-
Patent number: 10714086Abstract: Some implementations are directed to selective invocation of a particular third-party (3P) agent by an automated assistant to achieve an intended action determined by the automated assistant during a dynamic dialog between the automated assistant and a user. In some of those implementations, the particular 3P agent is invoked with value(s) for parameter(s) that are determined during the dynamic dialog; and/or the particular 3P agent is selected, from a plurality of candidate 3P agents, for invocation based on the determined value(s) for the parameter(s) and/or based on other criteria. In some of those implementations, the automated assistant invokes the particular 3P agent by transmitting, to the particular 3P agent, a 3P invocation request that includes the determined value(s) for the parameter(s).Type: GrantFiled: January 10, 2019Date of Patent: July 14, 2020Assignee: GOOGLE LLCInventors: Ulas Kirazci, Bo Wang, Steve Chen, Sunil Vemuri, Barnaby James, Valerie Nygaard
-
Publication number: 20200184974Abstract: Implementations relate to dynamically, and in a context-sensitive manner, biasing voice to text conversion. In some implementations, the biasing of voice to text conversions is performed by a voice to text engine of a local agent, and the biasing is based at least in part on content provided to the local agent by a third-party (3P) agent that is in network communication with the local agent. In some of those implementations, the content includes contextual parameters that are provided by the 3P agent in combination with responsive content generated by the 3P agent during a dialog that: is between the 3P agent, and a user of a voice-enabled electronic device; and is facilitated by the local agent. The contextual parameters indicate potential feature(s) of further voice input that is to be provided in response to the responsive content generated by the 3P agent.Type: ApplicationFiled: February 14, 2020Publication date: June 11, 2020Inventors: Barnaby James, Bo Wang, Sunil Vemuri, David Schairer, Ulas Kirazci, Ertan Dogrultan, Petar Aleksic
-
Patent number: 10600418Abstract: Implementations relate to dynamically, and in a context-sensitive manner, biasing voice to text conversion. In some implementations, the biasing of voice to text conversions is performed by a voice to text engine of a local agent, and the biasing is based at least in part on content provided to the local agent by a third-party (3P) agent that is in network communication with the local agent. In some of those implementations, the content includes contextual parameters that are provided by the 3P agent in combination with responsive content generated by the 3P agent during a dialog that: is between the 3P agent, and a user of a voice-enabled electronic device; and is facilitated by the local agent. The contextual parameters indicate potential feature(s) of further voice input that is to be provided in response to the responsive content generated by the 3P agent.Type: GrantFiled: December 7, 2016Date of Patent: March 24, 2020Assignee: GOOGLE LLCInventors: Barnaby James, Bo Wang, Sunil Vemuri, David Schairer, Ulas Kirazci, Ertan Dogrultan, Petar Aleksic
-
Patent number: 10490190Abstract: In various implementations, upon receiving a given voice command from a user, a voice-based trigger may be selected from a library of voice-based triggers previously used across a population of users. The library may include association(s) between each voice-based trigger and responsive action(s) previously performed in response to the voice-based trigger. The selecting may be based on a measure of similarity between the given voice command and the selected voice-based trigger. One or more responsive actions associated with the selected voice-based trigger in the library may be determined. Based on the one or more responsive actions, current responsive action(s) may be performed by a target client device selected based on sensor-dependent context. Feedback associated with performance of the current responsive action(s) may be received from the user and used to alter a strength of an association between the selected voice-based trigger and the one or more responsive actions.Type: GrantFiled: November 28, 2018Date of Patent: November 26, 2019Assignee: GOOGLE LLCInventors: Yuzhao Ni, Bo Wang, Barnaby James, Pravir Gupta, David Schairer
-
Patent number: 10297254Abstract: In various implementations, upon receiving a given voice command from a user, a voice-based trigger may be selected from a library of voice-based triggers previously used across a population of users. The library may include association(s) between each voice-based trigger and responsive action(s) previously performed in response to the voice-based trigger. The selecting may be based on a measure of similarity between the given voice command and the selected voice-based trigger. One or more responsive actions associated with the selected voice-based trigger in the library may be determined. Based on the one or more responsive actions, current responsive action(s) may be performed by the client device.Type: GrantFiled: October 3, 2016Date of Patent: May 21, 2019Assignee: GOOGLE LLCInventors: Yuzhao Ni, Bo Wang, Barnaby James, Pravir Gupta, David Schairer
-
Publication number: 20190147878Abstract: Some implementations are directed to selective invocation of a particular third-party (3P) agent by an automated assistant to achieve an intended action determined by the automated assistant during a dynamic dialog between the automated assistant and a user. In some of those implementations, the particular 3P agent is invoked with value(s) for parameter(s) that are determined during the dynamic dialog; and/or the particular 3P agent is selected, from a plurality of candidate 3P agents, for invocation based on the determined value(s) for the parameter(s) and/or based on other criteria. In some of those implementations, the automated assistant invokes the particular 3P agent by transmitting, to the particular 3P agent, a 3P invocation request that includes the determined value(s) for the parameter(s).Type: ApplicationFiled: January 10, 2019Publication date: May 16, 2019Inventors: Ulas Kirazci, Bo Wang, Steve Chen, Sunil Vemuri, Barnaby James, Valerie Nygaard
-
Publication number: 20190122657Abstract: Implementations relate to dynamically, and in a context-sensitive manner, biasing voice to text conversion. In some implementations, the biasing of voice to text conversions is performed by a voice to text engine of a local agent, and the biasing is based at least in part on content provided to the local agent by a third-party (3P) agent that is in network communication with the local agent. In some of those implementations, the content includes contextual parameters that are provided by the 3P agent in combination with responsive content generated by the 3P agent during a dialog that: is between the 3P agent, and a user of a voice-enabled electronic device; and is facilitated by the local agent. The contextual parameters indicate potential feature(s) of further voice input that is to be provided in response to the responsive content generated by the 3P agent.Type: ApplicationFiled: December 7, 2016Publication date: April 25, 2019Inventors: Barnaby James, Bo Wang, Sunil Vemuri, David Schairer, Ulas Kirazci, Ertan Dogrultan, Petar Aleksic
-
Publication number: 20190096406Abstract: In various implementations, upon receiving a given voice command from a user, a voice-based trigger may be selected from a library of voice-based triggers previously used across a population of users. The library may include association(s) between each voice-based trigger and responsive action(s) previously performed in response to the voice-based trigger. The selecting may be based on a measure of similarity between the given voice command and the selected voice-based trigger. One or more responsive actions associated with the selected voice-based trigger in the library may be determined. Based on the one or more responsive actions, current responsive action(s) may be performed by the client device. Feedback associated with performance of the current responsive action(s) may be received from the user and used to alter a strength of an association between the selected voice-based trigger and the one or more responsive actions.Type: ApplicationFiled: November 28, 2018Publication date: March 28, 2019Inventors: Yuzhao Ni, Bo Wang, Barnaby James, Pravir Gupta, David Schairer
-
Patent number: 10224031Abstract: Some implementations are directed to selective invocation of a particular third-party (3P) agent by an automated assistant to achieve an intended action determined by the automated assistant during a dynamic dialog between the automated assistant and a user. In some of those implementations, the particular 3P agent is invoked with value(s) for parameter(s) that are determined during the dynamic dialog; and/or the particular 3P agent is selected, from a plurality of candidate 3P agents, for invocation based on the determined value(s) for the parameter(s) and/or based on other criteria. In some of those implementations, the automated assistant invokes the particular 3P agent by transmitting, to the particular 3P agent, a 3P invocation request that includes the determined value(s) for the parameter(s).Type: GrantFiled: December 30, 2016Date of Patent: March 5, 2019Assignee: GOOGLE LLCInventors: Ulas Kirazci, Bo Wang, Steve Chen, Sunil Vemuri, Barnaby James, Valerie Nygaard
-
Publication number: 20180190274Abstract: Some implementations are directed to selective invocation of a particular third-party (3P) agent by an automated assistant to achieve an intended action determined by the automated assistant during a dynamic dialog between the automated assistant and a user. In some of those implementations, the particular 3P agent is invoked with value(s) for parameter(s) that are determined during the dynamic dialog; and/or the particular 3P agent is selected, from a plurality of candidate 3P agents, for invocation based on the determined value(s) for the parameter(s) and/or based on other criteria. In some of those implementations, the automated assistant invokes the particular 3P agent by transmitting, to the particular 3P agent, a 3P invocation request that includes the determined value(s) for the parameter(s).Type: ApplicationFiled: December 30, 2016Publication date: July 5, 2018Inventors: Ulas Kirazci, Bo Wang, Steve Chen, Sunil Vemuri, Barnaby James, Valerie Nygaard
-
Publication number: 20180166074Abstract: Methods, apparatus, and computer readable media are described related to recording, organizing, and making audio files available for consumption by voice-activated products. In various implementations, in response to receiving an input from a first user indicating that the first user intends to record audio content, audio content may be captured and stored. Input may be received from the first user indicating at least one identifier for the audio content. The stored audio content may be associated with the at least one identifier. A voice input may be received from a subsequent user. In response to determining that the voice input has particular characteristics, speech recognition may be biased in respect of the voice input towards recognition of the at least one identifier. In response to recognizing, based on the biased speech recognition, presence of the at least one identifier in the voice input, the stored audio content may be played.Type: ApplicationFiled: December 14, 2016Publication date: June 14, 2018Inventors: Vikram Aggarwal, Barnaby James
-
Publication number: 20180096681Abstract: In various implementations, upon receiving a given voice command from a user, a voice-based trigger may be selected from a library of voice-based triggers previously used across a population of users. The library may include association(s) between each voice-based trigger and responsive action(s) previously performed in response to the voice-based trigger. The selecting may be based on a measure of similarity between the given voice command and the selected voice-based trigger. One or more responsive actions associated with the selected voice-based trigger in the library may be determined. Based on the one or more responsive actions, current responsive action(s) may be performed by the client device. Feedback associated with performance of the current responsive action(s) may be received from the user and used to alter a strength of an association between the selected voice-based trigger and the one or more responsive actions.Type: ApplicationFiled: October 3, 2016Publication date: April 5, 2018Inventors: Yuzhao Ni, Bo Wang, Barnaby James, Pravir Gupta, David Schairer
-
Patent number: 9491150Abstract: Various embodiments described herein each provide one or more of systems, methods, software, and data structures that facilitate document-authorized access to a shared workspace. Some of these embodiments provide access to a shared workspace, such as a document review comment repository, through data embedded within a document. Mere possession of a document with a key, or other data element, allows a possessor of the document to participate in a workflow process.Type: GrantFiled: September 24, 2015Date of Patent: November 8, 2016Assignee: Adobe Systems IncorporatedInventors: Randy L. Swineford, Barnaby James, Patrick R. Wibbeler
-
Publication number: 20160014097Abstract: Various embodiments described herein each provide one or more of systems, methods, software, and data structures that facilitate document-authorized access to a shared workspace. Some of these embodiments provide access to a shared workspace, such as a document review comment repository, through data embedded within a document. Mere possession of a document with a key, or other data element, allows a possessor of the document to participate in a workflow process.Type: ApplicationFiled: September 24, 2015Publication date: January 14, 2016Inventors: RANDY L. SWINEFORD, BARNABY JAMES, PATRICK R. WIBBELER
-
Patent number: 9166954Abstract: Various embodiments described herein each provide one or more of systems, methods, software, and data structures that facilitate document-authorized access to a shared workspace. Some of these embodiments provide access to a shared workspace, such as a document review comment repository, through data embedded within a document. Mere possession of a document with a key, or other data element, allows a possessor of the document to participate in a workflow process.Type: GrantFiled: February 29, 2008Date of Patent: October 20, 2015Assignee: Adobe Systems IncorporatedInventors: Randy L. Swineford, Barnaby James, Patrick R. Wibbeler
-
Patent number: 9130905Abstract: Techniques for content review with proxy comment management are presented. Comments associated with content review are managed separately from the content itself. Some comments are associated with participants internal to a secure network where the comments are managed while other comments are originally received from external participants located outside the secure network. The external comments are adopted by one or more of the internal participants that act as proxies for the external participants and their supplied comments. The proxy relationship permits the external comments to be added to the comments for the content review within the secure network.Type: GrantFiled: September 18, 2006Date of Patent: September 8, 2015Assignee: ADOBE SYSTEMS INCORPORATEDInventors: Randy L. Swineford, Barnaby James
-
Publication number: 20140033294Abstract: Techniques for content review with proxy comment management are presented. Comments associated with content review are managed separately from the content itself. Some comments are associated with participants internal to a secure network where the comments are managed while other comments are originally received from external participants located outside the secure network. The external comments are adopted by one or more of the internal participants that act as proxies for the external participants and their supplied comments. The proxy relationship permits the external comments to be added to the comments for the content review within the secure network.Type: ApplicationFiled: September 18, 2006Publication date: January 30, 2014Inventors: Randy L. Swineford, Barnaby James
-
Publication number: 20140032500Abstract: Various embodiments provide one or more of systems, methods, and software that replicate a document workspace, including comments and participant information. Some embodiments allow participants to view and manipulate comments while a network connection is not available. Additionally, the document typically contains knowledge of a comment repository holding comments submitted by participants which eliminates a need for a comment discovery mechanism. Some embodiments provide various means for viewing, modifying, and adding comments even while disconnected from the network. Comments made while disconnected may later be pushed to the repository when a connection becomes available. Further embodiments may provide a background notification via a user interface to notify participants when new comments are received or new reviewers are added.Type: ApplicationFiled: October 31, 2007Publication date: January 30, 2014Inventors: Pat Wibbeler, Steve Dakin, Barnaby James, Randy L. Swineford
-
Publication number: 20140029751Abstract: Various embodiments described herein each provide one or more of systems, methods, software, and data structures that facilitate document-authorized access to a shared workspace. Some of these embodiments provide access to a shared workspace, such as a document review comment repository, through data embedded within a document. Mere possession of a document with a key, or other data element, allows a possessor of the document to participate in a workflow process.Type: ApplicationFiled: February 29, 2008Publication date: January 30, 2014Applicant: Adobe Systems IncorporatedInventors: Randy L. Swineford, Barnaby James, Patrick R. Wibbeler
-
Patent number: 8244796Abstract: Embodiments for customizing the presentation of a notification list are disclosed. In one example implementation, a method is provided for assembling a notification list including a plurality of tags to specify at least in part how the notification list is to be displayed by a client, and then causing the notification list to be transmitted to the client. In one example implementation, a method is provided including receiving, by a client, a notification list, where the notification list includes a plurality of tags to specify at least in part how the notification list is to be displayed, and causing the notification list to be displayed by the client in a manner specified at least in part by the plurality of tags.Type: GrantFiled: May 31, 2005Date of Patent: August 14, 2012Assignee: Adobe Systems IncorporatedInventors: Barnaby James, Scott E. Petersen