公开(公告)号：US12067331B2

公开(公告)日：2024-08-20

申请号：US18041152

申请日：2020-08-10

Applicant: Google LLC ,  Robert Marchant ,  Amelia Schladow ,  David Matthew Jones ,  Philip Roadley-Battin ,  Henry John Holland

Inventor： Robert Marchant ,  Amelia Schladow ,  David Matthew Jones ,  Philip Roadley-Battin ,  Henry John Holland

IPC: G06F3/048 ,  G06F3/0346 ,  G06F3/04847 ,  G06F3/0485 ,  G06F3/0488 ,  G06F3/16 ,  H04R1/10

CPC classification number: G06F3/165 ,  G06F3/0346 ,  G06F3/04847 ,  G06F3/0485 ,  G06F3/0488 ,  H04R1/1041 ,  H04R2420/07

Abstract: A computing system can implement a computer-implemented method for providing selective control of an acoustic environment of a user. The computer-implemented method can include determining a selected audio source of a plurality of audio sources in an environment of a user based at least in part on a selection user input at a peripheral device, where the peripheral device is in communication with the computing system. The computer-implemented method can include receiving a configuration user input at the peripheral device, where the configuration user input is indicative of an intent to configure an audio characteristic associated with the selected audio source. The computer-implemented method can include, in response to receiving the configuration user input, configuring the audio characteristic associated with the selected audio source based at least in part on the configuration user input.

公开(公告)号：US20240331296A1

公开(公告)日：2024-10-03

申请号：US18574846

申请日：2021-08-24

Applicant: Google LLC

Inventor： Robert Marchant ,  Tríona Éidín Butler ,  Henry John Holland ,  David Matthew Jones ,  Benjamin Guy Alexander Pawle ,  Michael Colville ,  George Joseph Rickerby

IPC: G06T17/20 ,  G06T13/40 ,  G06T19/20 ,  G06V40/16

CPC classification number: G06T17/20 ,  G06T13/40 ,  G06T19/20 ,  G06T2210/52 ,  G06T2219/024 ,  G06T2219/2016 ,  G06V40/171

Abstract: The technology provides enhanced co-presence of interactive media participants without high quality video or other photo-realistic representations of the participants. A low-resolution graphical representation (318) of a participant provides real-time dynamic co-presence. Face detection captures a maximum amount of facial expression with minimum detail in order to construct the low-resolution graphical representation. A set of facial mesh data (304) is generated by the face detection to include a minimal amount of information about the participant's face per frame. The mesh data, such as facial key points, is provided to one or more user devices so that the graphical representation of the participant can be rendered in a shared app at the other device(s) (308, 804). The rendering can include generating a hull (314, 806) that delineates a perimeter of the user mask and generating a set of facial features (316, 808), in which the graphical representation is assembled by combining the hull and the set of facial features (318, 810).

公开(公告)号：US20220291789A1

公开(公告)日：2022-09-15

申请号：US17626265

申请日：2019-07-11

Applicant: Google LLC

Inventor： David Matthew Jones ,  Robert Marchant

IPC: G06F3/0482 ,  G06F3/04812 ,  G06F3/0488

Abstract: A computing system can include an artificial intelligence system including one or more machine-learned models. The artificial intelligence system can be configured to receive context data and output data descriptive of a plurality of available control actions available for performance by the artificial intelligence system on behalf of a user of the computing system. The computing system can be configured to perform operations including obtaining the context data; inputting the context data into the artificial intelligence system; receiving, as an output of the artificial intelligence system, the data descriptive of the plurality of available control actions available for performance by the artificial intelligence system; and providing, within a user interface for display to a user, an artificial intelligence control surface. The artificial intelligence control surface can include a plurality of user-selectable tiles. The plurality of user-selectable tiles can respectively correspond to the plurality of available control actions.

公开(公告)号：US20230315378A1

公开(公告)日：2023-10-05

申请号：US18041152

申请日：2020-08-10

Applicant: Google LLC

Inventor： Robert Marchant ,  Amelia Schladow ,  David Matthew Jones ,  Philip Roadley-Battin ,  Henry John Holland

IPC: G06F3/16 ,  G06F3/0346 ,  G06F3/0485 ,  G06F3/0488 ,  G06F3/04847 ,  H04R1/10

CPC classification number: G06F3/165 ,  G06F3/0346 ,  G06F3/0485 ,  G06F3/0488 ,  G06F3/04847 ,  H04R1/1041 ,  H04R2420/07

Abstract: A computing system can implement a computer-implemented method for providing selective control of an acoustic environment of a user. The computer-implemented method can include determining a selected audio source of a plurality of audio sources in an environment of a user based at least in part on a selection user input at a peripheral device, where the peripheral device is in communication with the computing system. The computer-implemented method can include receiving a configuration user input at the peripheral device, where the configuration user input is indicative of an intent to configure an audio characteristic associated with the selected audio source. The computer-implemented method can include, in response to receiving the configuration user input, configuring the audio characteristic associated with the selected audio source based at least in part on the configuration user input.

公开(公告)号：US20230156401A1

公开(公告)日：2023-05-18

申请号：US17919931

申请日：2020-04-22

Applicant: Robert MARCHANT ,  David Matthew JONES ,  Philip ROADLEY-BATTIN ,  Amelia SCHLADOW ,  Henry John HOLLAND ,  Google LLC

Inventor： Robert Marchant ,  David Matthew Jones ,  Phillip Roadley-Battin ,  Amelia Schladow ,  Henry John Holland

IPC: H04R3/00 ,  H04R1/10 ,  G10K11/178

CPC classification number: H04R3/005 ,  H04R1/1041 ,  G10K11/17823 ,  H04R2460/07

Abstract: Systems and methods for generating audio presentations are provided. A method can include obtaining data indicative of an acoustic environment for a user; obtaining data indicative of one or more events; generating, by an artificial intelligence system, an audio presentation for the user based at least in part on the data indicative of the one or more events and the data indicative of the acoustic environment for the user; and presenting the audio presentation to the user. The acoustic environment can include at least one of a first audio signal playing on the computing system or a second audio signal associated with a surrounding environment of the user. The one or more events can include at least one of information to be conveyed by the computing system to the user or at least a portion of the second audio signal associated with the surrounding environment of the user.

公开(公告)号：US20240361980A1

公开(公告)日：2024-10-31

申请号：US18767223

申请日：2024-07-09

Applicant: Google LLC

Inventor： Robert Marchant ,  Amelia Schladow ,  David Matthew Jones ,  Philip Roadley-Battin ,  Henry John Holland

IPC: G06F3/16 ,  G06F3/0346 ,  G06F3/04847 ,  G06F3/0485 ,  G06F3/0488 ,  H04R1/10

CPC classification number: G06F3/165 ,  G06F3/0346 ,  G06F3/04847 ,  G06F3/0485 ,  G06F3/0488 ,  H04R1/1041 ,  H04R2420/07

Abstract: A computing system can implement a computer-implemented method for providing selective control of an acoustic environment of a user. The computer-implemented method can include determining a selected audio source of a plurality of audio sources in an environment of a user based at least in part on a selection user input at a peripheral device, where the peripheral device is in communication with the computing system. The computer-implemented method can include receiving a configuration user input at the peripheral device, where the configuration user input is indicative of an intent to configure an audio characteristic associated with the selected audio source. The computer-implemented method can include, in response to receiving the configuration user input, configuring the audio characteristic associated with the selected audio source based at least in part on the configuration user input.

公开(公告)号：US11500477B2

公开(公告)日：2022-11-15

申请号：US16025632

申请日：2018-07-02

Applicant: Google LLC

Inventor： Robert Marchant ,  David Matthew Jones ,  Henry John Holland ,  Alexander George Hulme ,  Fiona Paula O'Leary ,  Julie Mareva Arrive

IPC: G06N20/00 ,  G06T19/20 ,  G06V20/20 ,  G06V20/00 ,  G06F3/0354

Abstract: The present disclosure provides systems and methods that include or otherwise leverage an artificial intelligence system and/or provide user interface mechanisms particularly suited for interacting and/or interfacing with an artificial intelligence system. A computing system can include a camera, a light-emitting device, and an artificial intelligence system that comprises one or more machine-learned models. The computing system can include a processor and one or more non-transitory computer-readable media that stores instructions that, when executed, cause the processor to obtain an image of a scene captured by the camera; generate an attention output that describes at least one region of the scene that includes a subject of a processing operation performed by the artificial intelligence system; and control the light-emitting device to emit light onto or adjacent a region of the scene that includes the subject of the processing operation performed by the artificial intelligence system.

公开(公告)号：US20200004351A1

公开(公告)日：2020-01-02

申请号：US16025632

申请日：2018-07-02

Applicant: Google LLC

Inventor： Robert Marchant ,  David Matthew Jones ,  Henry John Holland ,  Alexander George Hulme ,  Fiona Paula O'Leary ,  Julie Mareva Arrive

IPC: G06F3/0354 ,  G06K9/00 ,  G06T19/20 ,  G06F15/18

Abstract: The present disclosure provides systems and methods that include or otherwise leverage an artificial intelligence system and/or provide user interface mechanisms particularly suited for interacting and/or interfacing with an artificial intelligence system. A computing system can include a camera, a light-emitting device, and an artificial intelligence system that comprises one or more machine-learned models. The computing system can include a processor and one or more non-transitory computer-readable media that stores instructions that, when executed, cause the processor to obtain an image of a scene captured by the camera; generate an attention output that describes at least one region of the scene that includes a subject of a processing operation performed by the artificial intelligence system; and control the light-emitting device to emit light onto or adjacent a region of the scene that includes the subject of the processing operation performed by the artificial intelligence system.