Inventor

Matthew Sharifi

Inventor

Kilchberg, CH

Overview

2012–2021

Patent span

Physics

Primary field (CPC G)

Patents· 220 as inventor

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

G06Fprimary

G06FElectric digital data processing31%

G10LSpeech analysis techniques or speech synthesis21%

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

G06QInformation and communication technology [ict] specially adapted for administrative, commercial, financial, managerial or supervisory purposes7%

G06VImage or video recognition or understanding6%

H04NPictorial communication, e.g. television5%

H04WWireless communication networks4%

G06KGraphical data reading3%

G10HElectrophonic musical instruments3%

G06NComputing arrangements based on specific computational models2%

PatentTitleYear

11,120,090On-device query rewriting2021 11,113,604Training 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 communication2021 11,089,457Personalized entity repository2021 11,064,227Systems and methods for live media content matching2021 11,062,709Providing pre-computed hotword models2021 11,056,120Segment-based speaker verification using dynamically generated phrases2021 11,038,824Inline responses to video or voice messages2021 11,003,987Audio processing with neural networks2021 10,970,646Action suggestions for user-selected content2021 10,963,630Sharing screen content in a mobile environment2021 10,958,695Methods, systems, and media for recommending content based on network conditions2021 10,923,100Adaptive text-to-speech outputs2021 10,909,987Hotword detection on multiple devices2021 10,878,318Adaptive artificial neural network selection techniques2020 10,867,600Recorded media hotword trigger suppression2020 10,866,974Dynamic display of content consumption by geographic location2020 10,860,639Query response using media consumption history2020 10,809,968Determining that audio includes music and then identifying the music as a particular song2020 10,803,391Modeling personal entities on a mobile device using embeddings2020 10,803,408Screen-analysis based device security2020 10,776,187Selective obfuscation of notifications2020 10,770,112Aggregation of related media content2020 10,769,428On-device image recognition2020 10,761,802Identifying music as a particular song2020 10,755,171Hiding and detecting information using neural networks2020 10,739,982Drag-and-drop on a mobile device2020 10,733,360Simulated hyperlinks on a mobile device2020 10,699,710Detecting and suppressing voice queries2020 10,664,519Visual recognition using user tap locations2020 10,663,313Providing traffic warnings to a user based on return journey2020 10,659,399Message analysis using a machine learning model2020 10,652,706Entity disambiguation in a mobile environment2020 10,650,828Hotword recognition2020 10,643,614Promoting voice actions to hotwords2020 10,621,987Providing pre-computed hotword models2020 10,592,261Automating user input from onscreen content2020 10,593,330Hotword detection on multiple devices2020 10,565,996Speaker identification2020 10,536,733Systems and methods for live media content matching2020 10,515,133Systems and methods for automatically suggesting metadata for media content2019 10,509,531Grouping and summarization of messages based on topics2019 10,504,524Segment-based speaker verification using dynamically generated phrases2019 10,497,373Providing pre-computed hotword models2019 10,491,660Sharing screen content in a mobile environment2019 10,489,410Mapping images to search queries2019 10,467,820Image style transfer for three-dimensional models2019 10,460,747Frequency based audio analysis using neural networks2019 10,453,441Adaptive text-to-speech outputs2019 10,446,153Providing pre-computed hotword models2019 10,438,591Hotword-based speaker recognition2019 10,424,321Audio data classification2019 10,387,461Techniques for suggesting electronic messages based on user activity and other context2019 10,367,770Notification bundles for affinities between notification data2019 10,353,950Visual recognition using user tap locations2019 10,346,223Selective obfuscation of notifications2019 10,346,493On-device query rewriting2019 10,318,543Obtaining and enhancing metadata for content items2019 10,320,939Video playlists and recommendations based on electronic messaging communications2019 10,311,249Selectively obscuring private information based on contextual information2019 10,303,779Media consumption history2019 10,305,828Search query predictions by a keyboard2019 10,299,089Contextually prompting users to switch communication modes2019 10,283,129Audio matching using time-frequency onsets2019 10,275,464Media consumption history2019 10,269,346Multiple speech locale-specific hotword classifiers for selection of a speech locale2019 10,262,659Hotword recognition2019 10,255,922Speaker identification using a text-independent model and a text-dependent model2019 10,248,440Providing a set of user input actions to a mobile device to cause performance of the set of user input actions2019 10,242,029Dynamic display of content consumption by geographic location2019 10,244,369Screen capture image repository for a user2019 10,241,668Drag-and-drop on a mobile device2019 10,242,378Incentive-based check-in2019 10,198,442Media consumption history2019 10,199,069Aggregation on related media content2019 10,186,264Promoting voice actions to hotwords2019 10,186,268Providing pre-computed hotword models2019 10,178,527Personalized entity repository2019 10,170,112Detecting and suppressing voice queries2019 10,147,197Segment content displayed on a computing device into regions based on pixels of a screenshot image that captures the content2018 10,140,998Method for siren detection based on audio samples2018 10,140,991Using audio characteristics to identify speakers and media items2018 10,133,533Automatic detection and correction of misalignment between display devices2018 10,134,398Hotword detection on multiple devices2018 10,120,934Hold back and real time ranking of results in a streaming matching system2018 10,109,270Adaptive text-to-speech outputs2018 10,109,276Promoting voice actions to hotwords2018 10,080,114Detection and ranking of entities from mobile onscreen content2018 10,078,803Screen-analysis based device security2018 10,069,783Notification bundles for affinities between notification data2018 10,055,390Simulated hyperlinks on a mobile device based on user intent and a centered selection of text2018 10,037,760Segment-based speaker verification using dynamically generated phrases2018 10,013,552Protecting content on a mobile device from mining2018 9,934,783Hotword recognition2018 9,928,840'Hotword recognition'2018 9,916,328'Providing user assistance from interaction understanding'2018 9,911,419'Providing pre-computed hotword models'2018 9,886,461'Indexing mobile onscreen content'2018 9,886,942'Adaptive text-to-speech outputs'2018 9,877,071Detection of creative works on broadcast media2018 9,870,345'Textual message ordering based on message content'2018 9,870,623'Segmenting content displayed on a computing device into regions based on pixels of a screenshot image that captures the content'2018 9,842,602'Method for siren detection based on audio samples'2017 9,836,597Protecting content on a mobile device from mining2017 9,824,079'Providing actions for mobile onscreen content'2017 9,817,907'Using place of accommodation as a signal for ranking reviews and point of interest search results'2017 9,811,352'Replaying user input actions using screen capture images'2017 9,805,719'Initiating actions based on partial hotwords'2017 9,798,708'Annotating relevant content in a screen capture image'2017 9,799,324'Adaptive text-to-speech outputs'2017 9,788,179'Detection and ranking of entities from mobile onscreen content'2017 9,786,279'Answering questions using environmental context'2017 9,762,651'Redaction suggestion for sharing screen content'2017 9,754,026'Hold back and real time ranking of results in a streaming matching system'2017 9,756,005'Notification bundles for affinities between notification data'2017 9,747,926'Hotword recognition'2017 9,741,348'Segment-based speaker verification using dynamically generated phrases'2017 9,720,955'Search query predictions by a keyboard'2017 9,711,148'Dual model speaker identification'2017 9,703,541'Entity action suggestion on a mobile device'2017 9,704,483'Collaborative language model biasing'2017 9,699,597'Wireless signal forwarding'2017 9,684,693'On-device query rewriting'2017 9,679,573'System and method for adding pitch shift resistance to an audio fingerprint'2017 9,674,497'Editing media content without transcoding'2017 9,661,361'Systems and methods for live media content matching'2017 9,646,612'Providing pre-computed hotword models'2017 9,619,854'Fingerprint matching for recommending media content within a viewing session'2017 9,620,114'Initiating actions based on partial hotwords'2017 9,606,716'Drag-and-drop on a mobile device'2017 9,589,564'Multiple speech locale-specific hotword classifiers for selection of a speech locale'2017 9,582,482'Providing an annotation linking related entities in onscreen content'2017 9,576,576'Answering questions using environmental context'2017 9,569,405'Generating correlation scores'2017 9,569,532'Melody recognition systems'2017 9,563,671'Protecting content on a mobile device from mining'2017 9,542,942'Promoting voice actions to hotwords'2017 9,542,488'Associating audio tracks with video content'2017 9,542,948'Text-dependent speaker identification'2017 9,536,151'Detection of inactive broadcasts during live stream ingestion'2017 9,529,907'Hold back and real time ranking of results in a streaming matching system'2016 9,520,130'Providing pre-computed hotword models'2016 9,514,752'Hotword detection on multiple devices'2016 9,514,753'Speaker identification using hash-based indexing'2016 9,508,342'Initiating actions based on partial hotwords'2016 9,508,023'Transformation invariant media matching'2016 9,502,026'Initiating actions based on partial hotwords'2016 9,484,064'Video chunking for robust, progressive uploading'2016 9,477,709'Query response using media consumption history'2016 9,471,673'Audio matching using time-frequency onsets'2016 9,443,512'Initiating actions based on partial hotwords'2016 9,435,878'Positioning using audio recognition'2016 9,424,846'Segment-based speaker verification using dynamically generated phrases'2016 9,411,884'Noise based interest point density pruning'2016 9,401,146'Identification of communication-related voice commands'2016 9,401,000'Protecting content on a mobile device from mining'2016 9,390,719'Interest points density control for audio matching'2016 9,384,273'Compressed patch features for audio fingerprinting'2016 9,384,734'Real-time audio recognition using multiple recognizers'2016 9,367,887'Multi-channel audio video fingerprinting'2016 9,344,759'Associating audio tracks of an album with video content'2016 9,330,663'Initiating actions based on partial hotwords'2016 9,323,770'Fingerprint merging after claim generation'2016 9,318,107'Hotword detection on multiple devices'2016 9,280,599'Interface for real-time audio recognition'2016 9,275,427'Multi-channel audio video fingerprinting'2016 9,275,136'Method for siren detection based on audio samples'2016 9,268,845'Audio matching using time alignment, frequency alignment, and interest point overlap to filter false positives'2016 9,263,042'Providing pre-computed hotword models'2016 9,263,035'Promoting voice actions to hotwords'2016 9,240,183'Reference signal suppression in speech recognition'2016 9,224,118'Dynamic display of content consumption by geographic location'2015 9,224,385'Unified recognition of speech and music'2015 9,213,703'Pitch shift and time stretch resistant audio matching'2015 9,208,225'Incentive-based check-in'2015 9,208,154'IDF weighting of LSH bands for live reference ingestion'2015 9,204,101'Video chunking for robust, progressive uploading'2015 9,202,472'Magnitude ratio descriptors for pitch-resistant audio matching'2015 9,189,826'Multi-channel audio video fingerprinting'2015 9,159,327'System and method for adding pitch shift resistance to an audio fingerprint'2015 9,159,364'Aggregation of related media content'2015 9,153,239'Differentiating between near identical versions of a song'2015 9,148,738'Using local gradients for pitch resistant audio matching'2015 9,129,015'Min/max filter for audio matching'2015 9,123,330'Large-scale speaker identification'2015 9,111,537'Real-time audio recognition protocol'2015 9,113,202'Inverted client-side fingerprinting and matching'2015 9,098,576'Ensemble interest point detection for audio matching'2015 9,087,124'Adaptive weighting of popular reference content in audio matching'2015 9,069,849'Methods for enforcing time alignment for speed resistant audio matching'2015 9,055,376'Classifying music by genre using discrete cosine transforms'2015 9,052,986'Pitch shift resistant audio matching'2015 9,031,840'Identifying media content'2015 9,026,540'Systems and methods for information match scoring'2015 9,008,490'Melody recognition systems'2015 9,002,835'Query response using media consumption history'2015 8,953,811'Full digest of an audio file for identifying duplicates'2015 8,938,089'Detection of inactive broadcasts during live stream ingestion'2015 8,918,382'Learning common spelling errors through content matching'2014 8,895,830'Interactive game based on user generated music content'2014 8,886,543'Frequency ratio fingerprint characterization for audio matching'2014 8,868,223'Positioning using audio recognition'2014 8,863,182'In-stream video stitching'2014 8,843,369'Speech endpointing based on voice profile'2014 8,838,609'IDF weighting of LSH bands for live reference ingestion'2014 8,831,763'Intelligent interest point pruning for audio matching'2014 8,812,320'Segment-based speaker verification using dynamically generated phrases'2014 8,805,683'Real-time audio recognition protocol'2014 8,805,560'Noise based interest point density pruning'2014 8,775,191'Efficient utterance-specific endpointer triggering for always-on hotwording'2014 8,768,712'Initiating actions based on partial hotwords'2014 8,738,633'Transformation invariant media matching'2014 8,735,708'System and method for synchronizing tag history'2014 8,719,039'Promoting voice actions to hotwords'2014 8,699,862'Synchronized content playback related to content recognition'2014 8,655,657'Identifying media content'2014 8,488,943'Trimming media content without transcoding'2013 8,484,017'Identifying media content'2013 8,458,156'Learning common spelling errors through content matching'2013 8,433,577'Detection of creative works on broadcast media'2013 8,212,135'Systems and methods for facilitating higher confidence matching by a computer-based melody matching system'2012

Career & activity timeline

Assembled from patent assignee/location history and declaration credentials.

2012–2021Patents assigned to GOOGLE INC (145)· patent assignee history

2012–2016Patents assigned to SHARIFI MATTHEW (30)· patent assignee history

2012–2016Patents assigned to POSTELNICU GHEORGHE (11)· patent assignee history

2012–2021Based in Zurich, CH· patent location history

2014–2016Patents assigned to ROBLEK DOMINIK (18)· patent assignee history

2014–2019Based in Palo Alto, CA, US· patent location history

2014–2019Based in Santa Clara, CA, US· patent location history

2016–2021Based in Kilchberg, CH· patent location history

2016–2020Based in Mountain View, CA, US· patent location history

2017–2021Patents assigned to GOOGLE LLC (100)· patent assignee history

Inventor activity

Assignee and location history derived from the patent record.

Assignees

Assignee	Patents	Span
GOOGLE INC	145	2012–2021
GOOGLE LLC	100	2017–2021
SHARIFI MATTHEWself	30	2012–2016
ROBLEK DOMINIK	18	2014–2016
POSTELNICU GHEORGHE	11	2012–2016

Locations

Location	Patents	Span
Kilchberg, CH	102	2016–2021
Zurich, CH	61	2012–2021
Palo Alto, California, US	33	2014–2019
Santa Clara, California, US	14	2014–2019
Mountain View, California, US	5	2016–2020