Patents by Inventor Jinyu Li

Jinyu Li has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Publication number: 20210020166
    Abstract: Streaming machine learning unidirectional models is facilitated by the use of embedding vectors. Processing blocks in the models apply embedding vectors as input. The embedding vectors utilize context of future data (e.g., data that is temporally offset into the future within a data stream) to improve the accuracy of the outputs generated by the processing blocks. The embedding vectors cause a temporal shift between the outputs of the processing blocks and the inputs to which the outputs correspond. This temporal shift enables the processing blocks to apply the embedding vector inputs from processing blocks that are associated with future data.
    Type: Application
    Filed: July 19, 2019
    Publication date: January 21, 2021
    Inventors: Jinyu Li, Amit Kumar Agarwal, Yifan Gong, Harini Kesavamoorthy
  • Patent number: 10885900
    Abstract: Improvements in speech recognition in a new domain are provided via the student/teacher training of models for different speech domains. A student model for a new domain is created based on the teacher model trained in an existing domain. The student model is trained in parallel to the operation of the teacher model, with inputs in the new and existing domains respectfully, to develop a neural network that is adapted to recognize speech in the new domain. The data in the new domain may exclude transcription labels but rather are parallelized with the data analyzed in the existing domain analyzed by the teacher model. The outputs from the teacher model are compared with the outputs of the student model and the differences are used to adjust the parameters of the student model to better recognize speech in the second domain.
    Type: Grant
    Filed: August 11, 2017
    Date of Patent: January 5, 2021
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Jinyu Li, Michael Lewis Seltzer, Xi Wang, Rui Zhao, Yifan Gong
  • Publication number: 20200363890
    Abstract: A display substrate, a manufacturing method thereof and a touch display device are disclosed. The display substrate includes a plurality of pixel units arranged in an array, every column of pixel units is provided with one corresponding first data line, every adjacent three columns of pixel units constitute one pixel unit group, and one second data line and one touch signal line are provided between every adjacent two pixel unit groups; between every adjacent two pixel unit groups, the second data line and the first data line are located at two sides of the touch signal line, respectively; and for the pixel unit adjacent to the second data line, a coupling capacitance between the pixel unit and the first data line adjacent to the pixel unit is as same as a coupling capacitance between the pixel unit and the second data line adjacent to the pixel unit.
    Type: Application
    Filed: April 24, 2019
    Publication date: November 19, 2020
    Applicants: BEIJING BOE OPTOELECTRONICS TECHNOLOGY CO., LTD., BOE TECHNOLOGY GROUP CO., LTD.
    Inventors: Dong WANG, Yue LI, Wang GUO, Mingyang LV, Yu ZHAO, Yanchen LI, Hailong WANG, Hongbo FENG, Jinyu LI
  • Patent number: 10839822
    Abstract: Representative embodiments disclose mechanisms to separate and recognize multiple audio sources (e.g., picking out individual speakers) in an environment where they overlap and interfere with each other. The architecture uses a microphone array to spatially separate out the audio signals. The spatially filtered signals are then input into a plurality of separators, so each signal is input into a corresponding signal. The separators use neural networks to separate out audio sources. The separators typically produce multiple output signals for the single input signals. A post selection processor then assesses the separator outputs to pick the signals with the highest quality output. These signals can be used in a variety of systems such as speech recognition, meeting transcription and enhancement, hearing aids, music information retrieval, speech enhancement and so forth.
    Type: Grant
    Filed: November 6, 2017
    Date of Patent: November 17, 2020
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Zhuo Chen, Jinyu Li, Xiong Xiao, Takuya Yoshioka, Huaming Wang, Zhenghao Wang, Yifan Gong
  • Publication number: 20200333582
    Abstract: An electrowetting display panel includes a plurality of subpixels. Each of the plurality of subpixels having a subpixel area and an hater-subpixel area. The electrowetting display panel includes a first substrate, including a first insulating layer, a first electrode layer on the first insulating layer, and a first lyophobic layer on a side of the first electrode layer away from the first insulating layer; a second substrate facing the first substrate, including a second electrode layer, and a second lyophobic layer on the second electrode layer; and a plurality of sealing elements between the first substrate and the second substrate to define a plurality of fluid channels, each of the plurality of sealing elements being in the inter-subpixel area. The electrowetting display panel includes a first fluid reservoir and a respective one of the plurality of fluid channels between the first lyophobic layer and the second lyophobic layer.
    Type: Application
    Filed: January 7, 2019
    Publication date: October 22, 2020
    Applicants: BEIJING BOE OPTOELECTRONICS TECHNOLOGY CO., LTD., BOE Technology Group Co., Ltd.
    Inventors: Mingyang Lv, Yue Li, Yanchen Li, Jinyu Li, Yu Zhao, Dawei Feng, Wang Guo
  • Publication number: 20200335085
    Abstract: Embodiments are associated with a speaker-independent acoustic model capable of classifying senones based on input speech frames and on first parameters of the speaker-independent acoustic model, a speaker-dependent acoustic model capable of classifying senones based on input speech frames and on second parameters of the speaker-dependent acoustic model, and a discriminator capable of receiving data from the speaker-dependent acoustic model and data from the speaker-independent acoustic model and outputting a prediction of whether received data was generated by the speaker-dependent acoustic model based on third parameters.
    Type: Application
    Filed: July 2, 2019
    Publication date: October 22, 2020
    Inventors: Zhong MENG, Jinyu LI, Yifan GONG
  • Publication number: 20200334526
    Abstract: According to some embodiments, a machine learning model may include an input layer to receive an input signal as a series of frames representing handwriting data, speech data, audio data, and/or textual data. A plurality of time layers may be provided, and each time layer may comprise a uni-directional recurrent neural network processing block. A depth processing block may scan hidden states of the recurrent neural network processing block of each time layer, and the depth processing block may be associated with a first frame and receive context frame information of a sequence of one or more future frames relative to the first frame. An output layer may output a final classification as a classified posterior vector of the input signal. For example, the depth processing block may receive the context from information from an output of a time layer processing block or another depth processing block of the future frame.
    Type: Application
    Filed: May 13, 2019
    Publication date: October 22, 2020
    Inventors: Jinyu LI, Vadim MAZALOV, Changliang LIU, Liang LU, Yifan GONG
  • Publication number: 20200334527
    Abstract: According to some embodiments, a universal modeling system may include a plurality of domain expert models to each receive raw input data (e.g., a stream of audio frames containing speech utterances) and provide a domain expert output based on the raw input data. A neural mixture component may then generate a weight corresponding to each domain expert model based on information created by the plurality of domain expert models (e.g., hidden features and/or row convolution). The weights might be associated with, for example, constrained scalar numbers, unconstrained scaler numbers, vectors, matrices, etc. An output layer may provide a universal modeling system output (e.g., an automatic speech recognition result) based on each domain expert output after being multiplied by the corresponding weight for that domain expert model.
    Type: Application
    Filed: May 16, 2019
    Publication date: October 22, 2020
    Inventors: Amit DAS, Jinyu LI, Changliang LIU, Yifan GONG
  • Publication number: 20200335082
    Abstract: A CS CTC model may be initialed from a major language CTC model by keeping network hidden weights and replacing output tokens with a union of major and secondary language output tokens. The initialized model may be trained by updating parameters with training data from both languages, and a LID model may also be trained with the data. During a decoding process for each of a series of audio frames, if silence dominates a current frame then a silence output token may be emitted. If silence does not dominate the frame, then a major language output token posterior vector from the CS CTC model may be multiplied with the LID major language probability to create a probability vector from the major language. A similar step is performed for the secondary language, and the system may emit an output token associated with the highest probability across all tokens from both languages.
    Type: Application
    Filed: May 13, 2019
    Publication date: October 22, 2020
    Inventors: Jinyu LI, Guoli YE, Rui ZHAO, Yifan GONG, Ke LI
  • Publication number: 20200335108
    Abstract: To generate substantially domain-invariant and speaker-discriminative features, embodiments are associated with a feature extractor to receive speech frames and extract features from the speech frames based on a first set of parameters of the feature extractor, a senone classifier to identify a senone based on the received features and on a second set of parameters of the senone classifier, an attention network capable of determining a relative importance of features extracted by the feature extractor to domain classification, based on a third set of parameters of the attention network, a domain classifier capable of classifying a domain based on the features and the relative importances, and on a fourth set of parameters of the domain classifier; and a training platform to train the first set of parameters of the feature extractor and the second set of parameters of the senone classifier to minimize the senone classification loss, train the first set of parameters of the feature extractor to maximize the dom
    Type: Application
    Filed: July 26, 2019
    Publication date: October 22, 2020
    Inventors: Zhong MENG, Jinyu LI, Yifan GONG
  • Publication number: 20200335122
    Abstract: To generate substantially condition-invariant and speaker-discriminative features, embodiments are associated with a feature extractor capable of extracting features from speech frames based on first parameters, a speaker classifier capable of identifying a speaker based on the features and on second parameters, and a condition classifier capable of identifying a noise condition based on the features and on third parameters. The first parameters of the feature extractor and the second parameters of the speaker classifier are trained to minimize a speaker classification loss, the first parameters of the feature extractor are further trained to maximize a condition classification loss, and the third parameters of the condition classifier are trained to minimize the condition classification loss.
    Type: Application
    Filed: June 7, 2019
    Publication date: October 22, 2020
    Inventors: Zhong MENG, Yong ZHAO, Jinyu LI, Yifan GONG
  • Publication number: 20200334538
    Abstract: Embodiments are associated with conditional teacher-student model training. A trained teacher model configured to perform a task may be accessed and an untrained student model may be created. A model training platform may provide training data labeled with ground truths to the teacher model to produce teacher posteriors representing the training data. When it is determined that a teacher posterior matches the associated ground truth label, the platform may conditionally use the teacher posterior to train the student model. When it is determined that a teacher posterior does not match the associated ground truth label, the platform may conditionally use the ground truth label to train the student model. The models might be associated with, for example, automatic speech recognition (e.g., in connection with domain adaptation and/or speaker adaptation).
    Type: Application
    Filed: May 13, 2019
    Publication date: October 22, 2020
    Inventors: Zhong MENG, Jinyu LI, Yong ZHAO, Yifan GONG
  • Publication number: 20200326447
    Abstract: The present disclosure relates to a collimator and a collimator mounting device and method, which belong to the technical field of accessories of the X-ray security inspection machine. The collimator comprises a T-shaped base plate and two lead plates, wherein the two lead plates are arranged side by side and in parallel to each other, and are fixed on a longitudinal plate of the T-shaped base plate and extends to a transverse plate of the T-shaped base plate. The collimator is inserted obliquely into a shielding box, with a gap between the two lead plates in the collimator aligned with a first ray opening.
    Type: Application
    Filed: August 9, 2017
    Publication date: October 15, 2020
    Inventors: Ximeng Li, Qinchan Wang, Zhongrong Yang, Jinyu Zhang
  • Publication number: 20200306750
    Abstract: An electrowetting panel includes a base substrate; an electrode array layer, including a plurality of electrodes arranged into an array; an insulating hydrophobic layer; a microfluidic channel layer located on the base substrate. Each electrode of the plurality of electrodes is connected to a driving circuit, and a droplet can move along a first direction by applying an electric voltage on each electrode. The insulating hydrophobic layer is located on the electrode array layer, and the microfluidic channel layer is located on the insulating hydrophobic layer. The electrodes includes a plurality of driving electrodes and a plurality of detecting electrodes. Along the first direction, a number N of the driving electrodes is located between every two adjacent detecting electrodes, where N is a natural number. The electrowetting panel also includes a detecting chip electrically connected to the detecting electrodes.
    Type: Application
    Filed: June 12, 2019
    Publication date: October 1, 2020
    Inventors: Baiquan LIN, Kerui XI, Junting OUYANG, Jinyu LI, Xiaohe LI
  • Patent number: 10706806
    Abstract: A pixel driving circuit includes a pixel unit including a blue sub-pixel connected to a data line to receive a data voltage, and a limit circuit connected between the data line and a reference voltage line configured to transfer a fixed DC voltage, the limit circuit being configured to limit the received data voltage when the received data voltage exceeds a voltage threshold.
    Type: Grant
    Filed: April 12, 2018
    Date of Patent: July 7, 2020
    Assignees: BEIJING BOE OPTOELECTRONICS TECHNOLOGY CO., LTD., BOE TECHNOLOGY GROUP CO., LTD.
    Inventors: Yu Zhao, Yue Li, Yanchen Li, Jinyu Li, Dong Wang, Shaojun Hou, Mingyang Lv, Dawei Feng, Wang Guo
  • Publication number: 20200175335
    Abstract: Representative embodiments disclose machine learning classifiers used in scenarios such as speech recognition, image captioning, machine translation, or other sequence-to-sequence embodiments. The machine learning classifiers have a plurality of time layers, each layer having a time processing block and a depth processing block. The time processing block is a recurrent neural network such as a Long Short Term Memory (LSTM) network. The depth processing blocks can be an LSTM network, a gated Deep Neural Network (DNN) or a maxout DNN. The depth processing blocks account for the hidden states of each time layer and uses summarized layer information for final input signal feature classification. An attention layer can also be used between the top depth processing block and the output layer.
    Type: Application
    Filed: November 30, 2018
    Publication date: June 4, 2020
    Inventors: Jinyu Li, Liang Lu, Changliang Liu, Yifan Gong
  • Publication number: 20200171491
    Abstract: A digital microfluidic chip and a digital microfluidic system. The digital microfluidic chip comprises: an upper substrate and a lower substrate arranged opposite to each other; multiple driving circuits and multiple addressing circuits disposed between the lower substrate and the upper substrate; and a control circuit, electrically connected to the driving circuits and the addressing circuits. The control circuit is configured to apply, in a driving stage, a driving voltage to each driving circuit, such that a droplet is controlled to move inside a droplet accommodation space according to a set path, measure, in a detection stage, after a bias voltage is applied to each addressing circuit, a charge loss amount of each addressing circuit, and to determine the position of the droplet according to the charge loss amount. The charge loss amount of each addressing circuit is related to the intensity of received external light.
    Type: Application
    Filed: July 26, 2019
    Publication date: June 4, 2020
    Inventors: Mingyang LV, Yue LI, Yanchen LI, Jinyu LI, Dawei FENG, Yu ZHAO, Dong WANG, Wang GUO, Hailong WANG, Yue GENG, Peizhi CAI, Fengchun PANG, Le GU, Chuncheng CHE, Haochen CUI, Yingying ZHAO, Nan ZHAO, Yuelei XIAO, Huyi LIAO
  • Patent number: 10650226
    Abstract: Systems and methods for identifying a false representation of a human face are provided. In one example, a method for identifying a false representation of a human face includes receiving one or more data streams captured by one or more sensors sensing a candidate face. In a plurality of stages that each comprises a different analysis, one or more of the data streams are analyzed, and the stages comprise determining whether a plurality of candidate face depth points lies on a single flat plane or a curving plane. Based at least in part on determining that the plurality of candidate face depth points lies on the single flat plane, an indication of the false representation of the human face is outputted.
    Type: Grant
    Filed: June 19, 2018
    Date of Patent: May 12, 2020
    Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC
    Inventors: Chun-Te Chu, Michael J. Conrad, Dijia Wu, Jinyu Li
  • Patent number: 10649564
    Abstract: A touch display panel and a display device are disclosed. The touch display panel includes a plurality of touch signal lines and a plurality of data lines disposed in a display area, and a plurality of lead terminals disposed in a peripheral area. The plurality of lead terminals includes a plurality of first terminals respectively connected to the plurality of data lines and a plurality of second terminals respectively connected to the plurality of touch signal lines. The plurality of lead terminals are arranged in a matrix. The first terminals and the second terminals are provided in a row direction or a column direction so as to be consistent with the sequence in which the data lines connected to the first terminals and the touch signal lines connected to the second terminals are arranged.
    Type: Grant
    Filed: July 28, 2017
    Date of Patent: May 12, 2020
    Assignees: BOE Technology Group Co., Ltd., Beijing BOE Optoelectronics Technology Co., Ltd.
    Inventors: Jinyu Li, Yue Li, Yanchen Li
  • Publication number: 20200143021
    Abstract: The use of user-specific data to process a biometric print, such that use of the biometric print is revoked by invalidating the user-specific data. The processed print is generated by performing one-way processing of the biometric print using the user-specific data. The processed print, not the biometric print, is then provided to the authentication system for later authentication of the user. During matching, the user later provides a current biometric, resulting in generation of a current biometric print. For each of multiple users, the user-specific is obtained for that user, and at least one processed print is generated for each user based on the current biometric print. The current processed prints are used by the authentication system to match against each of the enrolled processed prints. If a match is found, the user is identified as being the user associated with the matching enrolled print.
    Type: Application
    Filed: November 1, 2018
    Publication date: May 7, 2020
    Inventors: Peter Dawoud Shenouda DAWOUD, Rachel PETERS, Jinyu LI