Inventor

MATTHEW SHARIFI

Inventor

CH

Overview

2021–2026

Patent span

Physics

Primary field (CPC G)

Patents· 227 as inventor

Public. Assignee & technology derived from the patent record. Each patent links to its LexDana page.

G06Fprimary

G06FElectric digital data processing29%

G10LSpeech analysis techniques or speech synthesis27%

G06NComputing arrangements based on specific computational models9%

H04LTransmission of digital information, e.g. telegraphic communication8%

G06VImage or video recognition or understanding4%

G06QInformation and communication technology [ict] specially adapted for administrative, commercial, financial, managerial or supervisory purposes3%

H04WWireless communication networks3%

G01CMeasuring distances, levels or bearings3%

H04NPictorial communication, e.g. television3%

H04MTelephonic communication2%

PatentTitleYear

12,585,694Smart suggestions for image zoom regions2026 12,587,788Speaker array addressed by row and column selection2026 12,585,892Auto-translation of customized assistant2026 12,566,764Ambient multi-device framework for agent companions2026 12,566,965Training and/or utilizing an interaction prediction model to determine when to interact, and/or prompt for interaction, with an application on the basis of an electronic communication2026 12,566,076Ad-hoc navigation instructions2026 12,554,779Generating content items based on source document metadata using a generative neural network2026 12,555,577Hotphrase triggering based on a sequence of detections2026 12,554,972Performing tasks using generative neural networks2026 12,547,308Proactive modification or suggestion of assistant routines based on anticipated energy consumption2026 12,536,371On-device grammar checking2026 12,537,001Joint processing of corrective and misinterpreted utterances for accurate assistant responses2026 12,536,221Query response using media consumption history2026 12,526,247System(s) and method(s) for enabling a representative associated with an entity to modify a trained voice bot associated with the entity2026 12,518,749Adaptive sending or rendering of audio with text messages sent via automated assistant2026 12,518,744Selectively masking query content to provide to a secondary digital assistant2026 12,505,384Action suggestions for user-selected content2025 12,504,292Interactive voice navigation2025 12,499,886Document creation and editing via automated assistant interactions2025 12,489,720Inferring assistant action(s) based on ambient sensing by assistant device(s)2025 12,451,140Automatic generation and/or use of text-dependent speaker verification features2025 12,444,417Transferring actions from a shared device to a personal device associated with an account of a user2025 12,437,761Group hotwords2025 12,423,119Automated content switching rule for controlling access to interactive content on a computing device2025 12,411,919Shared assistant profiles verified via speaker identification2025 12,406,675Multi-user warm words2025 12,405,993Media consumption history2025 12,406,666Facilitating virtual or physical assistant interactions with virtual objects in a virtual environment2025 12,400,641Condition dependent scalable utilities for an automated assistant2025 12,399,023Message based navigational assistance2025 12,400,654Adapting hotword recognition based on personalized negatives2025 12,394,416Detecting near matches to a hotword or phrase2025 12,386,493Undoing application operation(s) via user interaction(s) with an automated assistant2025 12,380,879Distilling to a target device based on observed query patterns2025 12,380,169Methods and systems for presenting privacy friendly query activity based on environmental signal(s)2025 12,374,336Combining device or assistant-specific hotwords in a single utterance2025 12,374,331Transient personalization mode for guest users of an automated assistant2025 12,367,875Selecting between multiple automated assistants based on invocation properties2025 12,353,992Systems and methods for providing a machine-learned model with adjustable computational demand2025 12,356,041Integrating short-term context for content playback adaption2025 12,347,429Specifying preferred information sources to an assistant2025 12,347,430Automated assistant adaptation of a response to an utterance and/or of processing of the utterance, based on determined interaction measure2025 12,347,420Processing continued conversations over multiple devices2025 12,340,805Providing pre-computed hotword models2025 12,334,071Decaying automated speech recognition processing results2025 12,332,074Machine-learned foundational models for emulating conversational interactions between points of interest2025 12,322,376Personalized speech query endpointing based on prior interaction(s) involving a specific phrase preceding an endpoint2025 12,322,380Generating audio using auto-regressive generative neural networks2025 12,321,433Adaptive guest mode for portable speakers2025 12,316,624Screen-analysis based device security2025 12,314,850Audio processing with neural networks2025 12,315,506Biasing speech processing based on audibly rendered content, including dynamically adapting over duration of rendering2025 12,306,891Integration of web and media snippets into map applications2025 12,298,985Mapping images to search queries2025 12,296,471Selective interaction of robotic device with additional computing device(s)2025 12,300,250User-assigned custom assistant responses to queries being submitted by another user2025 12,294,848Spatial audio for device assistants2025 12,284,417Media arbitration2025 12,264,935Incorporating current and anticipated parking locations into directions suggestions2025 12,260,858Transferring dialog data from an initially invoked automated assistant to a subsequently invoked automated assistant2025 12,254,888Multi-factor audio watermarking2025 12,254,038Methods and systems for providing a secure automated assistant2025 12,254,885Detecting and handling failures in other assistants2025 12,254,884Hotword detection on multiple devices2025 12,247,842Requesting and receiving reminder instructions in a navigation session2025 12,246,676Supporting multiple roles in voice-enabled navigation2025 12,249,321Utilizing pre-event and post-event input streams to engage an automated assistant2025 12,242,472Combining parameters of multiple search queries that share a line of inquiry2025 12,230,252Generation of interactive audio tracks from visual content2025 12,223,960Adapting automated assistant functionality based on generated proficiency measure(s)2025 12,217,736Simultaneous acoustic event detection across multiple assistant devices2025 12,217,751Digital signal processor-based continued conversation2025 12,210,562Media consumption history2025 12,209,875Providing navigational instructions based on contextual data2025 12,205,591Voice query handling in an environment with multiple users2025 12,202,125Robotic computing device with adaptive user-interaction2025 12,205,588Detecting and suppressing voice queries2025 12,198,671Adaptive text-to-speech outputs based on language proficiency2025 12,197,818Automated assistant training and/or execution of inter-user procedures2025 12,190,892Selectively storing, with multiple user accounts and/or to a shared assistant device: speech recognition biasing, NLU biasing, and/or other data2025 12,183,348Generating and/or utilizing voice authentication biasing parameters for assistant devices2024 12,175,981Dynamically adapting on-device models, of grouped assistant devices, for cooperative processing of assistant requests2024 12,164,572Inferring semantic label(s) for assistant device(s) based on device-specific signal(s)2024 12,164,556Smart suggestions for image zoom regions2024 12,165,630Speech personalization and federated training using real world noise2024 12,164,584System and method for identifying places using contextual information2024 12,154,561Accelerometer-based endpointing measure(s) and /or gaze-based endpointing measure(s) for speech processing2024 12,154,576User authentication, for assistant action, using data from other device(s) in a shared environment2024 12,149,773Voice-based scene selection for video content on a computing device2024 12,147,470Handling contradictory queries on a shared device2024 12,147,652Annotating screen content in a mobile environment2024 12,137,132Methods, systems, and media for recommending content based on network conditions2024 12,136,412Training keyword spotters2024 12,132,944Systems and methods for live media content matching2024 12,117,308Navigation directions preview2024 12,111,834Ambient multi-device framework for agent companions2024 12,111,875Pairing user headphones with a location-based automated assistant2024 12,112,754Automated assistant for facilitating communications through dissimilar messaging features of different applications2024 12,108,314Personalized entity repository2024 12,106,755Warm word arbitration between automated assistant devices2024 12,094,454Multimodal intent understanding for automated assistant2024 12,096,321Contextually prompting users to switch communication modes2024 12,087,297Voice filtering other speakers from calls and audio messages2024 12,080,276Adapting automated speech recognition parameters based on hotword properties2024 12,080,293Combining responses from multiple automated assistants2024 12,073,826Freeze words2024 12,067,997Hotword-aware speech synthesis2024 12,057,119Contextual suppression of assistant command(s)2024 12,052,492Conditional camera control via automated assistant commands2024 12,051,408Promoting voice actions to hotwords2024 12,050,110Detecting and improving simultaneous navigation sessions on multiple devices2024 12,045,955Condition-aware generation of panoramic imagery2024 12,046,239Suggesting an alternative interface when environmental interference is expected to inhibit certain automated assistant interactions2024 12,038,977Visual recognition using user tap locations2024 12,038,299Content-aware navigation instructions2024 12,033,668Aggregation of related media content2024 12,026,593Action suggestions for user-selected content2024 12,002,468Providing pre-computed hotword models2024 11,996,094Automated assistant with audio presentation interaction2024 11,996,101Streaming action fulfillment based on partial hypotheses2024 11,990,121Distilling to a target device based on observed query patterns2024 11,984,128Automatic generation and/or use of text-dependent speaker verification features2024 11,972,764Providing related queries to a secondary automated assistant based on past interactions2024 11,972,766Detecting and suppressing commands in media that may trigger another automated assistant2024 11,960,526Query response using media consumption history2024 11,948,565Combining device or assistant-specific hotwords in a single utterance2024 11,947,783Undoing application operation(s) via user interaction(s) with an automated assistant2024 11,946,762Interactive voice navigation2024 11,935,519Preserving speech hypotheses across computing devices and/or dialog sessions2024 11,935,527Adapting automated assistant functionality based on generated proficiency measure(s)2024 11,924,150System(s) and method(s) for enabling a representative associated with an entity to modify a trained voice bot associated with the entity2024 11,924,149Composition of complex content via user interaction with an automated assistant2024 11,922,952User-assigned custom assistant responses to queries being submitted by another user2024 11,915,706Hotword detection on multiple devices2024 11,915,689Generating audio using auto-regressive generative neural networks2024 11,914,661Integration of web and media snippets into map applications2024 11,914,660Collaborative search sessions through an automated assistant2024 11,907,739Annotating screen content in a mobile environment2024 11,887,006Training and/or utilizing an interaction prediction model to determine when to interact, and/or prompt for interaction, with an application on the basis of an electronic communication2024 11,886,482Methods and systems for providing a secure automated assistant2024 11,886,524Limiting provision and display of redundant digital components on a client device2024 11,886,510Inferring semantic label(s) for assistant device(s) based on device-specific signal(s)2024 11,880,559Confidence level based controls on a second device2024 11,867,525Sharing a navigation session to minimize driver distraction2024 11,861,474Dynamic placement of computation sub-graphs2024 11,861,642Group action fulfillment across multiple user devices2024 11,862,155Group hotwords2024 11,853,346Media consumption history2023 11,847,561Adaptive artificial neural network selection techniques2023 11,838,582Media arbitration2023 11,830,486Detecting near matches to a hotword or phrase2023 11,823,680Automated assistant for facilitating communications through dissimilar messaging features of different applications2023 11,823,684Generating and/or utilizing voice authentication biasing parameters for assistant devices2023 11,823,664Correcting speech misrecognition of spoken utterances2023 11,817,106Selectively storing, with multiple user accounts and/or to a shared assistant device: speech recognition biasing, NLU biasing, and/or other data2023 11,814,062Detecting and handling driving event sounds during a navigation session2023 11,816,141Media consumption history2023 11,798,557Recorded media hotword trigger suppression2023 11,798,530Simultaneous acoustic event detection across multiple assistant devices2023 11,798,546Transient personalization mode for guest users of an automated assistant2023 11,790,005Methods and systems for presenting privacy friendly query activity based on environmental signal(s)2023 11,783,828Combining responses from multiple automated assistants2023 11,775,324Automated content switching rule for controlling access to interactive content on a computing device2023 11,776,549Multi-factor audio watermarking2023 11,765,452Conditional camera control via automated assistant commands2023 11,762,848Combining parameters of multiple search queries that share a line of inquiry2023 11,756,530Self-supervised pitch estimation2023 11,756,544Selectively providing enhanced clarification prompts in automated assistant interactions2023 11,748,660Automated assistant training and/or execution of inter-user procedures2023 11,749,267Adapting hotword recognition based on personalized negatives2023 11,749,284Dynamically adapting on-device models, of grouped assistant devices, for cooperative processing of assistant requests2023 11,741,944Speech personalization and federated training using real world noise2023 11,734,287Mapping images to search queries2023 11,727,925Cross-device data synchronization based on simultaneous hotword triggers2023 11,722,731Integrating short-term context for content playback adaption2023 11,716,600Personalized entity repository2023 11,704,136Automatic reminders in a mobile environment2023 11,694,685Hotphrase triggering based on a sequence of detections2023 11,688,392Freeze words2023 11,682,396Providing pre-computed hotword models2023 11,676,594Decaying automated speech recognition processing results2023 11,677,995Systems and methods for live media content matching2023 11,670,281Adaptive text-to-speech outputs based on language proficiency2023 11,657,817Suggesting an alternative interface when environmental interference is expected to inhibit certain automated assistant interactions2023 11,620,990Adapting automated speech recognition parameters based on hotword properties2023 11,586,341Structured response summarization of electronic messages2023 11,587,568Streaming action fulfillment based on partial hypotheses2023 11,573,810Sharing screen content in a mobile environment2023 11,574,640User-assigned custom assistant responses to queries being submitted by another user2023 11,568,879Segment-based speaker verification using dynamically generated phrases2023 11,568,870Automated assistant for facilitating communications through dissimilar messaging features of different applications2023 11,562,748Detecting and suppressing commands in media that may trigger another automated assistant2023 11,557,301Hotword-based speaker recognition2023 11,557,278Speaker dependent follow up actions and warm words2023 11,557,293Contextual suppression of assistant command(s)2023 11,557,299Hotword detection on multiple devices2023 11,557,300Detecting and handling failures in other assistants2023 11,558,546Conditional camera control via automated assistant commands2023 11,558,368Screen-analysis based device security2023 11,551,144Dynamic placement of computation sub-graphs2023 11,539,992Auto-adjust playback speed and contextual information2022 11,532,313Selectively storing, with multiple user accounts and/or to a shared assistant device: speech recognition biasing, NLU biasing, and/or other data2022 11,521,597Correcting speech misrecognition of spoken utterances2022 11,514,109Inferring semantic label(s) for assistant device(s) based on device-specific signal(s)2022 11,488,597Document creation and editing via automated assistant interactions2022 11,468,052Combining parameters of multiple search queries that share a line of inquiry2022 11,462,219Voice filtering other speakers from calls and audio messages2022 11,461,386Visual recognition using user tap locations2022 11,455,996Automated assistant adaptation of a response to an utterance and/or of processing of the utterance, based on determined interaction measure2022 11,425,072Inline responses to video or voice messages2022 11,423,885Utilizing pre-event and post-event input streams to engage an automated assistant2022 11,415,427Providing traffic warnings to a user based on return journey2022 11,412,065Video playlists and recommendations based on electronic messaging communications2022 11,410,192Group action fulfillment across multiple user devices2022 11,402,984Proximity-based controls on a second device2022 11,347,385Sharing screen content in a mobile environment2022 11,341,954Training keyword spotters2022 11,341,969Detecting and suppressing voice queries2022 11,335,380Aggregation of related media content2022 11,315,575Automatic generation and/or use of text-dependent speaker verification features2022 11,308,934Hotword-aware speech synthesis2022 11,304,041Contextually prompting users to switch communication modes2022 11,288,107Selective obfuscation of notifications2022 11,269,897Mapping images to search queries2022 11,257,498Recorded media hotword trigger suppression2022 11,256,472Determining that audio includes music and then identifying the music as a particular song2022 11,137,893Drag-and-drop on a mobile device2021

Career & activity timeline

Assembled from patent assignee/location history and declaration credentials.

2021–2026Patents assigned to GOOGLE LLC (225)· patent assignee history

2021–2026Based in CH· patent location history

2022–2025Based in US· patent location history

2023–2024Patents assigned to DEEPMIND TECH LTD (2)· patent assignee history

Inventor activity

Assignee and location history derived from the patent record.

Assignees

Assignee	Patents	Span
GOOGLE LLC	225	2021–2026
DEEPMIND TECH LTD	2	2023–2024

Locations

Location	Patents	Span
CH	217	2021–2026
US	10	2022–2025