公开(公告)号：US20220284899A1

公开(公告)日：2022-09-08

申请号：US17749892

申请日：2022-05-20

Applicant: GOOGLE LLC

Inventor： Alexander H. GRUENSTEIN ,  Aleksandar KRACUN ,  Matthew SHARIFI

IPC: G10L15/22 ,  G10L15/08 ,  G10L15/26 ,  H04L9/40 ,  G10L17/00

Abstract: A computing system receives requests from client devices to process voice queries that have been detected in local environments of the client devices. The system identifies that a value that is based on a number of requests to process voice queries received by the system during a specified time interval satisfies one or more criteria. In response, the system triggers analysis of at least some of the requests received during the specified time interval to trigger analysis of at least some received requests to determine a set of requests that each identify a common voice query. The system can generate an electronic fingerprint that indicates a distinctive model of the common voice query. The fingerprint can then be used to detect an illegitimate voice query identified in a request from a client device at a later time.

公开(公告)号：US20180336170A1

公开(公告)日：2018-11-22

申请号：US16050763

申请日：2018-07-31

Applicant: Google LLC

Inventor： Matthew SHARIFI ,  David PETROU

IPC: G06F17/22 ,  G06F9/48 ,  G06F9/451 ,  G06F3/0482 ,  G06F3/0484

Abstract: Systems and methods simulate a hyperlink in regular content displayed on a screen. An example method can include generating, responsive to detecting a simulated hyperlink indication, a centered selection from content displayed on a display of a computing device, providing the centered selection to a simulated hyperlink model that predicts an operation given the centered selection, and initiating the operation using an intent associated with a mobile application. The simulated hyperlink model may also provide, from the centered selection, an intelligent selection used the intent's parameter. Another method includes identifying documents having a hyperlink whitelisted websites, generating positive training examples for a simulated hyperlink model using the documents, each positive training example having a centered selection, a web site, and a mobile application mapped to the website, and training the simulated hyperlink model, using the positive training examples, to predict an operation for the mobile application given the centered selection.

公开(公告)号：US20210081794A1

公开(公告)日：2021-03-18

申请号：US17105033

申请日：2020-11-25

Applicant: GOOGLE LLC

Inventor： Matthew SHARIFI ,  Jakob Nicolaus FOERSTER

IPC: G06N3/08 ,  H04L29/06 ,  G06F9/50 ,  G06N3/04

Abstract: Computer-implemented techniques can include obtaining, by a client computing device, a digital media item and a request for a processing task on the digital item and determining a set of operating parameters based on (i) available computing resources at the client computing device and (ii) a condition of a network. Based on the set of operating parameters, the client computing device or a server computing device can select one of a plurality of artificial neural networks (ANNs), each ANN defining which portions of the processing task are to be performed by the client and server computing devices. The client and server computing devices can coordinate processing of the processing task according to the selected ANN. The client computing device can also obtain final processing results corresponding to a final evaluation of the processing task and generate an output based on the final processing results.

公开(公告)号：US20220343896A1

公开(公告)日：2022-10-27

申请号：US17640579

申请日：2020-09-25

Applicant: GOOGLE LLC

Inventor： Marco TAGLIASACCHI ,  Mihajlo VELIMIROVIC ,  Matthew SHARIFI ,  Dominik ROBLEK ,  Christian FRANK ,  Beat GFELLER

IPC: G10L15/06 ,  G10L25/30 ,  G10L25/90 ,  G10L21/013

Abstract: Example embodiments relate to techniques for training artificial neural networks or oilier machine-learning encoders to accurately predict the pitch of input audio samples in a semitone or otherwise logarithmically-scaled pitch space. An example method may include generating, from a sample of audio data, two training samples by applying two different pitch shifts to the sample of audio training data. This can be done by converting the sample of audio data into the frequency domain and then shifting the transformed data. These known shifts are then compared to the predicted pitches generated by applying the two training samples to the encoder. The encoder is then updated based on the comparison, such that the relative pitch output by the encoder is improved with respect to accuracy. One or more audio samples, labeled with absolute pitch values, can then be used to calibrate the relative pitch values generated by the trained encoder.

公开(公告)号：US20200348813A1

公开(公告)日：2020-11-05

申请号：US16935681

申请日：2020-07-22

Applicant: Google LLC

Inventor： Matthew SHARIFI ,  David PETROU

IPC: G06F3/0486 ,  G06F3/16 ,  G06F9/54 ,  G06F3/0484 ,  G06F3/0488

Abstract: Implementations provide an improved drag-and-drop operation on a mobile device. For example, a method includes identifying a drag area in a user interface of a first mobile application in response to a drag command and receiving a drop location in a second mobile application that differs from the first mobile application. The method may also include determining that a drop location is a text input control and the drag area is not text-based, performing a search for a text description of the drag area, and pasting the text description into the text input control. The method may also include determining that a drop location is an image input control and that the drag area is text based, performing a search using the drag area for a responsive image, and pasting the responsive image into the image input control.

公开(公告)号：US20190205005A1

公开(公告)日：2019-07-04

申请号：US16295638

申请日：2019-03-07

Applicant: Google LLC

Inventor： Matthew SHARIFI ,  David PETROU

IPC: G06F3/0486 ,  G06F3/0488 ,  G06F9/54 ,  G06F3/16 ,  G06F3/0484

CPC classification number: G06F3/0486 ,  G06F3/04842 ,  G06F3/0488 ,  G06F3/04883 ,  G06F3/167 ,  G06F9/543 ,  G06F2203/04803

Abstract: Implementations provide an improved drag-and-drop operation on a mobile device. For example, a method includes identifying a drag area in a user interface of a first mobile application in response to a drag command and receiving a drop location in a second mobile application that differs from the first mobile application. The method may also include determining that a drop location is a text input control and the drag area is not text-based, performing a search for a text description of the drag area, and pasting the text description into the text input control. The method may also include determining that a drop location is an image input control and that the drag area is text based, performing a search using the drag area for a responsive image, and pasting the responsive image into the image input control.

公开(公告)号：US20240119286A1

公开(公告)日：2024-04-11

申请号：US18542424

申请日：2023-12-15

Applicant: GOOGLE LLC

Inventor： Matthew SHARIFI ,  Jakob Nicolaus FOERSTER

IPC: G06N3/08 ,  G06F9/50 ,  G06N3/045 ,  H04L67/01

CPC classification number: G06N3/08 ,  G06F9/5044 ,  G06F9/505 ,  G06F9/5094 ,  G06N3/045 ,  H04L67/01 ,  Y02D10/00

Abstract: Computer-implemented techniques can include obtaining, by a client computing device, a digital media item and a request for a processing task on the digital item and determining a set of operating parameters based on (i) available computing resources at the client computing device and (ii) a condition of a network. Based on the set of operating parameters, the client computing device or a server computing device can select one of a plurality of artificial neural networks (ANNs), each ANN defining which portions of the processing task are to be performed by the client and server computing devices. The client and server computing devices can coordinate processing of the processing task according to the selected ANN. The client computing device can also obtain final processing results corresponding to a final evaluation of the processing task and generate an output based on the final processing results.

公开(公告)号：US20210295823A1

公开(公告)日：2021-09-23

申请号：US17342149

申请日：2021-06-08

Applicant: Google LLC

Inventor： Matthew SHARIFI

IPC: G10L15/06 ,  G11B27/036 ,  G11B27/10 ,  G11B27/34 ,  G10L25/78 ,  G10L15/26 ,  G06F3/16

Abstract: The method includes receiving sender media that was recorded by a sender device associated with a sender. The method further comprises playing, by a recipient device, the sender media for a recipient. The method further comprises detecting that the recipient is speaking. The method further comprises recording recipient media based on detecting that the recipient is speaking. The method further comprises determining a location in the sender media at which the recipient media is to be included. The method further comprises generating combined media that includes at least a portion of the sender media and the recipient media at the location.

公开(公告)号：US20200092237A1

公开(公告)日：2020-03-19

申请号：US16130650

申请日：2018-09-13

Applicant: Google LLC

Inventor： Matthew SHARIFI

IPC: H04L12/58 ,  H04N21/4788 ,  G10L15/18 ,  G06F17/30 ,  G06F3/16 ,  G10L25/93

Abstract: The method includes receiving sender media that was recorded by a sender device associated with a sender. The method further comprises playing, by a recipient device, the sender media for a recipient. The method further comprises detecting that the recipient is speaking. The method further comprises recording recipient media based on detecting that the recipient is speaking. The method further comprises determining a location in the sender media at which the recipient media is to be included. The method further comprises generating combined media that includes at least a portion of the sender media and the recipient media at the location.

公开(公告)号：US20190019110A1

公开(公告)日：2019-01-17

申请号：US16133395

申请日：2018-09-17

Applicant: Google LLC

Inventor： Matthew SHARIFI ,  Kai WANG ,  David PETROU

IPC: G06N99/00 ,  G06F21/31 ,  G06F21/36 ,  H04L29/06 ,  H04W4/02 ,  H04W12/06 ,  H04W4/80 ,  H04W12/10 ,  H04W12/12

CPC classification number: G06N20/00 ,  G06F21/316 ,  G06F21/36 ,  H04L63/083 ,  H04L63/102 ,  H04W4/029 ,  H04W4/80 ,  H04W12/00508 ,  H04W12/06 ,  H04W12/10 ,  H04W12/1206

Abstract: Systems and methods are provided for a content-based security for computing devices. An example method includes identifying content rendered by a mobile application, the content being rendered during a session, generating feature vectors from the content and determining that the feature vectors do not match a classification model. The method also includes providing, in response to the determination that the feature vectors do not match the classification model, a challenge configured to authenticate a user of the mobile device. Another example method includes determining a computing device is located at a trusted location, capturing information from a session, the information coming from content rendered by a mobile application during the session, generating feature vectors for the session, and repeating this until a training criteria is met. The method also includes training a classification model using the feature vectors and authenticating a user of the device using the trained classification model.