Inventor
Jinyu Li
Inventor
Redmond, WA, US
Overview
Patents· 52 as inventor
Public. Assignee & technology derived from the patent record. Each patent links to its LexDana page.
G10Lprimary
G10LSpeech analysis techniques or speech synthesis18%
G06FElectric digital data processing14%
G06VImage or video recognition or understanding12%
G06KGraphical data reading9%
G06TImage data processing or generation, in general9%
G06NComputing arrangements based on specific computational models7%
A63FCard, board, or roulette games6%
G02FOptical devices or arrangements for the control of light by modification of the optical properties of the media of the elements involved therein4%
G09GArrangements or circuits for control of indicating devices using static means to present variable information4%
H01LSemiconductor devices3%
PatentTitleYear
10,839,822Multi-channel speech separation202010,706,806Pixel driving circuit, array substrate and display device202010,649,564Touch display panel and display device202010,650,226False face representation identification202010,643,602Adversarial teacher-student learning for unsupervised domain adaptation202010,629,193Advancing word-based speech recognition processing202010,580,432Speech recognition using connectionist temporal classification202010,515,301Small-footprint deep neural network201910,452,935Spoofed face detection201910,409,134Electronic paper display panel, driving method and electronic paper display device201910,354,656Speaker recognition201910,347,241Speaker-invariant training via adversarial learning201910,260,936Frequency-sweep experimental method for predicting noise of power capacitor201910,203,789Touch display panel comprising a transparent conducting film layer, method for fabrication thereof and touch display device201910,175,546Array substrate and manufacturing method thereof, and display device201910,146,362Shift register unit, a shift register, a driving method, and an array substrate201810,139,971Touch display panel and display device201810,019,990Variable-component deep neural network for robust speech recognition201810,007,839False face representation identification20189,972,238Shift register and driving method therefor, gate drive circuit and display apparatus20189,933,824Centrifugal fan and an electronic device having the same20189,842,585'Multilingual deep neural network'20179,803,655'Airflow accelerating device and electronic apparatus'20179,728,184'Restructuring deep neural network acoustic models'20179,703,940'Managed biometric identity'20179,582,724'False face representation identification'20179,539,500'Biometric recognition'20179,532,485'Heat dissipating device and electronic apparatus'20169,520,127'Shared hidden layer combination for speech recognition systems'20169,454,958'Exploiting heterogeneous data in deep neural network-based speech recognition systems'20169,336,775'Posterior-based feature with partial distance elimination for speech recognition'20169,324,321'Low-footprint adaptation and personalization for a deep neural network'20169,278,287'Visual based identity tracking'20169,280,969'Model training for automatic speech recognition from imperfect transcription data'20169,251,427'False face representation identification'20169,165,180'Illumination sensitive face recognition'20159,070,360'Confidence calibration in automatic speech recognition systems'20158,926,431'Visual based identity tracking'20158,924,735'Managed biometric identity'20148,864,581'Visual based identitiy tracking'20148,824,749'Biometric recognition'20148,781,156'Voice-body identity correlation'20148,731,916'Online distorted speech estimation within an unscented transformation framework'20148,711,159'VGPU: a real time GPU emulator'20148,687,880'Real time head pose estimation'20148,352,241'Emulating legacy hardware using IEEE 754 compliant hardware'20138,265,341'Voice-body identity correlation'20128,237,720'Shader-based finite state machine frame detection'20128,239,195'Adapting a compressed model for use in speech recognition'20128,217,962'Single-pass bounding box calculation'20128,214,215'Phase sensitive model adaptation for noisy speech recognition'20128,180,637'High performance HMM adaptation with joint compensation of additive and convolutive distortions'2012Career & activity timeline
Assembled from patent assignee/location history and declaration credentials.
2012–2017Patents assigned to MICROSOFT CORP (20)· patent assignee history
2012–2016Patents assigned to LI JINYU (16)· patent assignee history
2012–2020Based in Redmond, WA, US· patent location history
2012–2020Based in Sammamish, WA, US· patent location history
2015–2020Patents assigned to MICROSOFT TECHNOLOGY LICENSING LLC (25)· patent assignee history
2015–2016Based in Bellevue, WA, US· patent location history
2016–2020Based in Beijing, CN· patent location history
2018–2020Patents assigned to BEIJING BOE OPTOELECTRONICS TECH CO LTD (7)· patent assignee history
2018–2020Patents assigned to BOE TECHNOLOGY GROUP CO LTD (7)· patent assignee history
2019Based in Shanghai, CN· patent location history
Inventor activity
Assignee and location history derived from the patent record.
Assignees
| Assignee | Patents | Span |
|---|---|---|
| MICROSOFT TECHNOLOGY LICENSING LLC | 25 | 2015–2020 |
| MICROSOFT CORP | 20 | 2012–2017 |
| LI JINYUself | 16 | 2012–2016 |
| BEIJING BOE OPTOELECTRONICS TECH CO LTD | 7 | 2018–2020 |
| BOE TECHNOLOGY GROUP CO LTD | 7 | 2018–2020 |
Locations
| Location | Patents | Span |
|---|---|---|
| Redmond, Washington, US | 21 | 2012–2020 |
| Sammamish, Washington, US | 16 | 2012–2020 |
| Beijing, CN | 10 | 2016–2020 |
| Bellevue, Washington, US | 2 | 2015–2016 |
| Shanghai, CN | 1 | 2019 |