Zhuo Chen, 46San Diego, CA

2022038, Dec 1, 2022

May 28, 2021

17/334570

- San Francisco CA, US
Bharath Ram Manoharan - Pleasanton CA, US
Peter Thang Doan - San Francisco CA, US
Shivakarthik Subramanyam - Dublin CA, US
Zhuo Yao Chen - Needham MA, US
Paul Sydell - San Rafael CA, US
Swadesh Raj Bhattarai - Fremont CA, US

G06F 16/23
G06F 16/27
G06F 16/21
G06F 9/48
G06F 11/14

An online system, such as a multi-tenant system ensures high availability of systems, for example, database management systems. The online system replicates the databases across multiple datacenters including: (1) a master node that receives read and write requests (2) a read-replica that receives only read requests and (3) a spare node that does not receive requests but acts as standby for high availability. One or more application servers may send read and write requests to the databases. The system performs a sweep of upgrades of the database nodes and also performs traffic quiescing of the requests received from the application servers to redirect the traffic across the database nodes as the upgrade sweep is orchestrated. The sweep of upgrades ensures that the availability of the database management system to the end users is maximized during the upgrade process.

2021040, Dec 30, 2021

Sep 13, 2021

17/473645

- Redmond WA, US
Andreas Stolcke - Berkeley CA, US
Zhuo Chen - Woodinville WA, US
Dimitrios Basile Dimitriadis - Bellevue WA, US
Nanshan Zeng - Bellevue WA, US
Lijuan Qin - Redmond WA, US
William Isaac Hinthorn - Seattle WA, US
Xuedong Huang - Bellevue WA, US

G10L 15/30
G10L 15/16
G10L 21/0208
G10L 21/0272

A computer implemented method includes receiving audio signals representative of speech via multiple audio streams transmitted from corresponding multiple distributed devices, performing, via a neural network model, continuous speech separation for one or more of the received audio signals having overlapped speech, and providing the separated speech on a fixed number of separate output audio channels.

2020034, Nov 5, 2020

Apr 30, 2019

16/398836

- Redmond WA, US
Andreas Stolcke - Berkeley CA, US
Zhuo Chen - Woodinville WA, US
Dimitrios Basile Dimitriadis - Bellevue WA, US
Nanshan Zeng - Bellevue WA, US
Lijuan Qin - Redmond WA, US
William Isaac Hinthorn - Seattle WA, US
Xuedong Huang - Bellevue WA, US

G06F 17/28
H04L 29/06
G10L 15/26
G10L 13/08

Systems and methods for providing customized output based on a user preference in a distributed system are provided. In example embodiments, a meeting server or system receives audio streams from a plurality of distributed devices involved in an intelligent meeting. The meeting system identifies a user corresponding to a distributed device of the plurality of distributed devices and determines a preferred language of the user. A transcript from the received audio streams is generated. The meeting system translates the transcript into the preferred language of the user to form a translated transcript. The translated transcript is provided to the distributed device of the user.

2020034, Nov 5, 2020

Apr 30, 2019

16/399152

- Redmond WA, US
Andreas Stolcke - Berkeley CA, US
Zhuo Chen - Woodinville WA, US
Dimitrios Basile Dimitriadis - Bellevue WA, US
Nanshan Zeng - Bellevue WA, US
Lijuan Qin - Redmond WA, US
William Isaac Hinthorn - Seattle WA, US
Xuedong Huang - Bellevue WA, US

G10L 15/26
H04R 1/40
H04L 29/06

A computer implemented method includes receiving audio streams at a meeting server from two distributed devices that are streaming audio captured during an ad-hoc meeting between at least two users, comparing the received audio streams to determine that the received audio streams are representative of sound from the ad-hoc meeting, generating a meeting instance to process the audio streams in response to the comparing determining that the audio streams are representative of sound from the ad-hoc meeting, and processing the received audio streams to generate a transcript of the ad-hoc meeting.

2020034, Nov 5, 2020

Apr 30, 2019

16/399166

- Redmond WA, US
Andreas Stolcke - Berkeley CA, US
Zhuo Chen - Woodinville WA, US
Dimitrios Basile Dimitriadis - Bellevue WA, US
Nanshan Zeng - Bellevue WA, US
Lijuan Qin - Redmond WA, US
William Isaac Hinthorn - Seattle WA, US
Xuedong Huang - Bellevue WA, US

G10L 15/26
G10L 15/08

A computer implemented method processes audio streams recorded during a meeting by a plurality of distributed devices. Operations include performing speech recognition on each audio stream by a corresponding speech recognition system to generate utterance-level posterior probabilities as hypotheses for each audio stream, aligning the hypotheses and formatting them as word confusion networks with associated word-level posteriors probabilities, performing speaker recognition on each audio stream by a speaker identification algorithm that generates a stream of speaker-attributed word hypotheses, formatting speaker hypotheses with associated speaker label posterior probabilities and speaker-attributed hypotheses for each audio stream as a speaker confusion network, aligning the word and speaker confusion networks from all audio streams to each other to merge the posterior probabilities and align word and speaker labels, and creating a best speaker-attributed word transcript by selecting the sequence of word and speaker labels with the highest posterior probabilities.

2020034, Nov 5, 2020

Apr 30, 2019

16/399175

- Redmond WA, US
Andreas Stolcke - Berkeley CA, US
Zhuo Chen - Woodinville WA, US
Dimitrios Basile Dimitriadis - Bellevue WA, US
Nanshan Zeng - Bellevue WA, US
Lijuan Qin - Redmond WA, US
William Isaac Hinthorn - Seattle WA, US
Xuedong Huang - Bellevue WA, US

G10L 15/30
G10L 15/16
G10L 21/0208
G10L 21/0272

A computer implemented method includes receiving audio signals representative of speech via multiple audio streams transmitted from corresponding multiple distributed devices, performing, via a neural network model, continuous speech separation for one or more of the received audio signals having overlapped speech, and providing the separated speech on a fixed number of separate output audio channels.

2019034, Nov 7, 2019

Jul 16, 2019

16/512926

- Wilmington DE, US
Lijun Dong - San Diego CA, US
Shamim Akbar Rahman - Cote St. Luc, CA
Quang Ly - North Wales PA, US
Xu Li - Plainsboro NJ, US
Zhuo Chen - Claymont DE, US

H04W 4/70
H04W 60/06
H04W 60/00
H04L 12/24
H04W 8/22
H04W 4/80
H04W 48/10

The present application describes a computer-implemented device on a network including a non-transitory memory having instructions stored thereon for registering a node with a router on the network. The device also includes a processor, operably coupled to the non-transitory memory, configured to execute the instructions of receiving, from the node over the network, a solicitation with context information including a registration start time request. The processor is also configured to execute the instructions of evaluating, at the router, whether to accept the solicitation based upon neighbor space and the received start time request. The processor is even further configured to execute the instructions of sending, to the node, an advertisement including an approved registration start time based upon the determining step.

2018035, Dec 6, 2018

Nov 10, 2017

15/809399

- Wilmington DE, US
Lijun DONG - San Diego CA, US
Shamim Akbar RAHMAN - Quebec, CA
Quang LY - North Wales PA, US
Xu LI - Plainsboro NJ, US
Zhuo CHEN - Claymont DE, US

H04W 4/70
H04W 60/06
H04W 60/00
H04W 48/10
H04W 4/80
H04L 12/24
H04W 8/22

The present application describes a computer-implemented device on a network including a non-transitory memory having instructions stored thereon for registering a node with a router on the network. The device also includes a processor, operably coupled to the non-transitory memory, configured to execute the instructions of receiving, from the node over the network, a solicitation with context information including a registration start time request. The processor is also configured to execute the instructions of evaluating, at the router, whether to accept the solicitation based upon neighbor space and the received start time request. The processor is even further configured to execute the instructions of sending, to the node, an advertisement including an approved registration start time based upon the determining step.