公开(公告)号：US11562748B2

公开(公告)日：2023-01-24

申请号：US17108705

申请日：2020-12-01

Applicant: Google LLC

Inventor： Matthew Sharifi ,  Victor Carbune

IPC: G10L17/22 ,  G06F3/16 ,  G10L19/018 ,  G10L25/51

Abstract: Techniques are described herein for detecting and suppressing commands in media that may trigger another automated assistant. A method includes: determining, for each of a plurality of automated assistant devices in an environment that are each executing at least one automated assistant, an active capability of the automated assistant device; initiating playback of digital media by an automated assistant; in response to initiating playback, processing the digital media to identify an audio segment in the digital media that, upon playback, is expected to trigger activation of at least one automated assistant executing on at least one of the plurality of automated assistant devices in the environment, based on the active capability of the at least one of the plurality of automated assistant devices; and in response to identifying the audio segment in the digital media, modifying the digital media to suppress the activation of the at least one automated assistant.

公开(公告)号：US11557300B2

公开(公告)日：2023-01-17

申请号：US17087358

申请日：2020-11-02

Applicant: Google LLC

Inventor： Victor Carbune ,  Matthew Sharifi

IPC: G10L15/32 ,  G10L15/22

Abstract: Techniques are described herein for detecting and handling failures in other automated assistants. A method includes: executing a first automated assistant in an inactive state at least in part on a computing device operated by a user; while in the inactive state, determining, by the first automated assistant, that a second automated assistant failed to fulfill a request of the user; in response to determining that the second automated assistant failed to fulfill the request of the user, the first automated assistant processing cached audio data that captures a spoken utterance of the user comprising the request that the second automated assistant failed to fulfill, or features of the cached audio data, to determine a response that fulfills the request of the user; and providing, by the first automated assistant to the user, the response that fulfills the request of the user.

公开(公告)号：US11521597B2

公开(公告)日：2022-12-06

申请号：US17011606

申请日：2020-09-03

Applicant: Google LLC

Inventor： Matthew Sharifi ,  Victor Carbune

IPC: G10L15/00 ,  G10L15/08 ,  G06F3/16 ,  G10L13/02

Abstract: Implementations can receive audio data corresponding to a spoken utterance of a user, process the audio data to generate a plurality of speech hypotheses, determine an action to be performed by an automated assistant based on the speech hypotheses, and cause the computing device to render an indication of the action. In response to the computing device rendering the indication, implementations can receive additional audio data corresponding to an additional spoken utterance of the user, process the additional audio data to determine that a portion of the spoken utterance is similar to an additional portion of the additional spoken utterance, supplant the action with an alternate action, and cause the automated assistant to initiate performance of the alternate action. Some implementations can determine whether to render the indication of the action based on a confidence level associated with the action.

公开(公告)号：US20220382802A1

公开(公告)日：2022-12-01

申请号：US17336000

申请日：2021-06-01

Applicant: GOOGLE LLC

Inventor： Matthew Sharifi ,  Victor Carbune

IPC: G06F16/532 ,  G06T3/40

Abstract: Techniques are described herein for providing smart suggestions for image zoom regions. A method includes: receiving a search query; performing a search using the search query to identify search results that include image search results including a plurality of images that are responsive to the search query; for a given image of the plurality of images included in the image search results, determining at least one zoom region in the given image; and providing the search results including the image search results, including providing the given image and an indication of the at least one zoom region in the given image.

公开(公告)号：US20220366903A1

公开(公告)日：2022-11-17

申请号：US17321994

申请日：2021-05-17

Applicant: GOOGLE LLC

Inventor： Victor Carbune ,  Matthew Sharifi ,  Ondrej Skopek ,  Justin Lu ,  Daniel Valcarce ,  Kevin Kilgour ,  Mohamad Hassan Rom ,  Nicolo D'Ercole ,  Michael Golikov

IPC: G10L15/22 ,  G10L15/18 ,  G10L15/05 ,  G10L25/78

Abstract: Some implementations process, using warm word model(s), a stream of audio data to determine a portion of the audio data that corresponds to particular word(s) and/or phrase(s) (e.g., a warm word) associated with an assistant command, process, using an automatic speech recognition (ASR) model, a preamble portion of the audio data (e.g., that precedes the warm word) and/or a postamble portion of the audio data (e.g., that follows the warm word) to generate ASR output, and determine, based on processing the ASR output, whether a user intended the assistant command to be performed. Additional or alternative implementations can process the stream of audio data using a speaker identification (SID) model to determine whether the audio data is sufficient to identify the user that provided a spoken utterance captured in the stream of audio data, and determine if that user is authorized to cause performance of the assistant command.

公开(公告)号：US11494667B2

公开(公告)日：2022-11-08

申请号：US15874121

申请日：2018-01-18

Applicant: Google LLC

Inventor： Victor Carbune ,  Thomas Deselaers

IPC: G06N5/04 ,  G06K9/62 ,  G06N20/00 ,  G06N3/04 ,  G06N3/08

Abstract: Example aspects of the present disclosure are directed to systems and methods that enable improved adversarial training of machine-learned models. An adversarial training system can generate improved adversarial training examples by optimizing or otherwise tuning one or hyperparameters that guide the process of generating of the adversarial examples. The adversarial training system can determine, solicit, or otherwise obtain a realism score for an adversarial example generated by the system. The realism score can indicate whether the adversarial example appears realistic. The adversarial training system can adjust or otherwise tune the hyperparameters to produce improved adversarial examples (e.g., adversarial examples that are still high-quality and effective while also appearing more realistic). Through creation and use of such improved adversarial examples, a machine-learned model can be trained to be more robust against (e.g., less susceptible to) various adversarial techniques, thereby improving model, device, network, and user security and privacy.

公开(公告)号：US11490172B2

公开(公告)日：2022-11-01

申请号：US17282492

申请日：2019-07-23

Applicant: Google LLC

Inventor： Victor Carbune ,  Andrii Maksai ,  Sandro Feuz

IPC: H04N21/8541 ,  H04N21/8405 ,  H04N21/845 ,  H04N21/8545

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, identify and classify the various video pathways in an interactive video based on the content of these video pathways. A video comprising multiple video segments is obtained from a video library. Each video segment is directly linked to at least one other video segment and the multiple video segments comprise a beginning segment, intermediate segments (including interactive segments), and final segments. Multiple video pathways in the video are identified. For each identified video pathway, classification data is generated and each such video pathway is then stored in the video library. When the video is selected from a particular category of the video library, the video segments of a video pathway that has a classification which is the same as the classification associated with the particular category, is then displayed.

公开(公告)号：US20220339542A1

公开(公告)日：2022-10-27

申请号：US17766146

申请日：2019-10-04

Applicant: GOOGLE LLC

Inventor： Alexandru-Marian Damian ,  Victor Carbune

IPC: A63F13/537 ,  G06V20/40 ,  G06T11/00

Abstract: The disclosed subject matter can receive a source video and identifies one or more player actions based on the source video. A second video can be received that is based on a currently executing game environment. A portion of the source video that exhibits a first gameplay situation that is similar to a gameplay situation in the second video can be determined. A property of the determined portion of the source video can be adjusted to produce a guide video. The guide video can be overlaid on the currently executing game environment.

公开(公告)号：US11483170B1

公开(公告)日：2022-10-25

申请号：US16730484

申请日：2019-12-30

Applicant: GOOGLE LLC

Inventor： Victor Carbune ,  Daniel Keysers ,  Thomas Deselaers

IPC: G06F15/16 ,  H04L12/18 ,  H04M3/56

Abstract: Systems and methods for video conference content auto-retrieval and focus based on learned relevance is provided. In accordance with the systems and methods, audio streams and video streams from client devices participating in a video conference are received. Based on the audio streams, a subject being discussed during the video conference at a point in time is determined. A video stream that is most relevant to the subject being discussed during the video conference at the point in time is determined from the video streams. The determined video stream is provided to the client devices for presentation on the client devices while the subject is being discussed during the video conference.

公开(公告)号：US11468052B2

公开(公告)日：2022-10-11

申请号：US16912298

申请日：2020-06-25

Applicant: Google LLC

Inventor： Matthew Sharifi ,  Victor Carbune

IPC: G06F17/00 ,  G06F16/242 ,  G06F16/2457 ,  G06K9/62 ,  G06F16/248 ,  G06F16/23

Abstract: Methods, systems, and computer readable media related to generating a combined search query based on search parameters of a current search query of a user and search parameters of one or more previously submitted search quer(ies) of the user that are determined to be of the same line of inquiry as the current search query. Two or more search queries may be determined to share a line of inquiry when it is determined that they are within a threshold level of semantic similarity to one another. Once a shared line of inquiry has been identified and a combined search query generated, users may interact with the search parameters and/or the search results to update the search parameters of the combined search query.