LexDanaLexDanabeta
Inventor

Trausti Kristjansson

Inventor
Mountain View, CA, US

Overview

61→
Patents
2007–2020
Patent span
Physics
Primary field (CPC G)

Patents· 61 as inventor

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

G10Lprimary
G10LSpeech analysis techniques or speech synthesis35%
G06FElectric digital data processing19%
H04RLoudspeakers, microphones, gramophone pick-ups or like acoustic electromechanical transducers9%
H04MTelephonic communication8%
H04BTransmission6%
H04WWireless communication networks6%
H04NPictorial communication, e.g. television4%
G06VImage or video recognition or understanding2%
H04LTransmission of digital information, e.g. telegraphic communication2%
G01SRadio direction-finding1%
PatentTitleYear
10,863,296Microphone failure detection and re-optimization202010,847,176Detection of TV state using sub-audible signal202010,777,214Method for efficient autonomous loudspeaker room adaptation202010,755,728Multichannel noise cancellation using frequency domain spectrum masking202010,720,176Multisensory speech detection202010,714,120Multisensory speech detection202010,685,664Analyzing noise levels to determine usability of microphones202010,672,394Word-level correction of speech input202010,622,004Acoustic echo cancellation using loudspeaker position202010,622,009Methods for detecting double-talk202010,614,173Auto-translation for multi user audio and video202010,560,737Voice-controlled multimedia device202010,553,236Multichannel noise cancellation using frequency domain spectrum masking202010,522,167Multichannel noise cancellation using deep neural network masking201910,372,831Auto-translation for multi user audio and video201910,304,475Trigger word based beam selection201910,218,818Matching encoder output to network bandwidth201910,147,439Volume adjustment for listening environment201810,127,918Methods for reconstructing an audio signal201810,026,419Multisensory speech detection201810,020,009Multisensory speech detection20189,947,338Echo latency estimation20189,892,731'Methods for speech enhancement and speech recognition using neural networks'20189,881,608'Word-level correction of speech input'20189,720,909'Auto-translation for multi user audio and video'20179,711,145'Word-level correction of speech input'20179,679,581'Sign-language video processor'20179,570,094'Multisensory speech detection'20179,542,932'Word-level correction of speech input'20179,466,287'Word-level correction of speech input'20169,263,048'Word-level correction of speech input'20169,123,339'Speech recognition using repeated utterances'20159,110,891'Auto-translation for multi user audio and video'20159,087,517'Word-level correction of speech input'20159,009,053'Multisensory speech detection'20158,983,845'Third-party audio subsystem enhancement'20158,862,474'Multisensory speech detection'20148,745,209'Matching encoder output to network bandwidth'20148,682,659'Geotagged environmental audio for enhanced speech recognition accuracy'20148,666,740'Speech and noise models for speech recognition'20148,504,185'Predictive pre-recording of audio for voice input'20138,494,852'Word-level correction of speech input'20138,478,590'Word-level correction of speech input'20138,468,012'Acoustic model adaptation using geographic information'20138,428,759'Predictive pre-recording of audio for voice input'20138,428,940'Metadata-based weighting of geotagged environmental audio for enhanced speech recognition accuracy'20138,265,928'Geotagged environmental audio for enhanced speech recognition accuracy'20128,249,868'Speech and noise models for speech recognition'20128,234,111'Speech and noise models for speech recognition'20128,219,384'Acoustic model adaptation using geographic information'20128,195,319'Predictive pre-recording of audio for voice input'20128,175,872'Geotagged and weighted environmental audio for enhanced speech recognition accuracy'20128,131,543'Speech detection'20127,827,297'Multimedia linking and synchronization method, presentation and editing apparatus'20107,664,643'System and method for speech separation and multi-talker speech recognition'20107,596,494'Method and apparatus for high resolution speech reconstruction'20097,486,815'Method and apparatus for scene learning and three-dimensional tracking using stereo video cameras'20097,458,029'System and process for controlling a shared display given inputs from multiple users using multiple input modalities'20087,426,496'Assisted form filling'20087,305,129'Methods and apparatus for populating electronic forms from scanned documents'20077,269,560'Speech detection and enhancement using audio/video fusion'2007

Career & activity timeline

Assembled from patent assignee/location history and declaration credentials.

2007–2009Based in Redmond, WA, US· patent location history
2012–2019Patents assigned to GOOGLE INC (31)· patent assignee history
2012–2015Patents assigned to KRISTJANSSON TRAUSTI (18)· patent assignee history
2012–2014Patents assigned to LLOYD MATTHEW I (11)· patent assignee history
2012–2020Based in Mountain View, CA, US· patent location history
2012–2019Based in Hartsdale, NY, US· patent location history
2018–2020Patents assigned to AMAZON TECH INC (14)· patent assignee history
2018–2020Patents assigned to GOOGLE LLC (9)· patent assignee history
2018–2020Based in San Jose, CA, US· patent location history
2020Based in Seattle, WA, US· patent location history

Inventor activity

Assignee and location history derived from the patent record.

Assignees
AssigneePatentsSpan
GOOGLE INC312012–2019
KRISTJANSSON TRAUSTIself182012–2015
AMAZON TECH INC142018–2020
LLOYD MATTHEW I112012–2014
GOOGLE LLC92018–2020
Locations
LocationPatentsSpan
Mountain View, California, US232012–2020
San Jose, California, US142018–2020
Hartsdale, New York, US142012–2019
Redmond, Washington, US52007–2009
Seattle, Washington, US12020