Microsoft Technology Licensing, LLC

Ordos Yuansheng Optoelectronics Co., Ltd.

Chinese Academy of Sciences

Beijing Boe Technology Development Co., Ltd.

Boe Technology Group Co., Ltd.

Shujie Liu

Yu Wu

Chengyi Wang

Jinyu Li

Liangliang Liu

Zhiyong Xue

Hailong Li

Lingling Ma

Hongyu Mi

Nanshan Zeng

Furu Wei

Xie Chen

Kenichi Kumatani

Xuedong David Huang

Yao Qian

Mingyuan Gao

Fengqin Hu

Xianyong Lu

Zhengyou Zhang

Ming Zhou

Philip Andrew Chou

Cha Zhang

Xu Bin Liu

Liman Peng

Qianqian Zhang

Qiang Chen

Nini Bai

Nan Duan

Duyu Tang

Daxin Jiang

Linjun Shou

Guodong Jing

Xie Sun

Long Zhou

Ming Gong

Wendi Wang

Embodiments are provided for building a configurable multilingual model. A computing system obtains a plurality of language-specific automatic speech recognition modules and a universal automatic speech recognition module trained on a multi-language training dataset comprising training data corresponding to each of the plurality of different languages. The computing system then compiles the universal automatic speech recognition module with the plurality of language-specific automatic speech recognition modules to generate a configurable multilingual model that is configured to selectively and dynamically utilize a sub-set of the plurality of language-specific automatic speech recognition modules with the universal automatic speech recognition module to process audio content in response to user input identifying one or more target languages associated with the audio content.

Canonical training for highly configurable multilingual speech

A system obtains a first training data set comprising labeled speech data or both labeled and unlabeled data corresponding to a high-resource data set as well as latent speech representations based on the first training data set. The system trains a machine learning model on the first training data set to learn phonetically aware speech representations corresponding to the first training data set. The system applies the latent speech representations to a transformer context network to generate contextual representations. The system aligns each of the contextual representations with a phoneme label to generate phonetically-aware contextual representations. The system causes a refinement engine to further refine the machine learning model.

Unified speech representation learning

The computing system trains an end-to-end (E2E) automatic speech recognition (ASR) model, using a transformer-transducer-based deep neural network that comprises a transformer encoder network and a transducer predictor network. The E2E ASR model is trained to have one or more adjustable hyperparameters that are configured to dynamically adjust an efficiency or a performance of the E2E ASR model when the E2E ASR model is deployed onto a device or executed by the device, by identifying one or more conditions of the device associated with computational power of the device and setting at least one of the one or more adjustable hyperparameters based on one or more conditions of the device.

Efficiency adjustable speech recognition system

Systems and methods are provided for training a machine learning model to learn speech representations. Labeled speech data or both labeled and unlabeled data sets is applied to a feature extractor of a machine learning model to generate latent speech representations. The latent speech representations are applied to a quantizer to generate quantized latent speech representations and to a transformer context network to generate contextual representations. Each contextual representation included in the contextual representations is aligned with a phoneme label to generate phonetically-aware contextual representations. Quantized latent representations are aligned with phoneme labels to generate phonetically aware latent speech representations. Systems and methods also include randomly replacing a sub-set of the contextual representations with quantized latent speech representations during their alignments to phoneme labels and aligning the phonetically aware latent speech representations to the contextual representations using supervised learning.

A computing system is configured to generate a transformer-transducer-based deep neural network. The transformer-transducer-based deep neural network comprises a transformer encoder network and a transducer predictor network. The transformer encoder network has a plurality of layers, each of which includes a multi-head attention network sublayer and a feed-forward network sublayer. The computing system trains an end-to-end (E2E) automatic speech recognition (ASR) model, using the transformer-transducer-based deep neural network. The E2E ASR model has one or more adjustable hyperparameters that are configured to dynamically adjust an efficiency or a performance of E2E ASR model when the E2E ASR model is deployed onto a device or executed by the device.

A method for preparing an array substrate, a display panel and an evaporation apparatus are disclosed. A method comprises: fixing a base substrate to an evaporation stage; attaching at least one shielding sheet to the base substrate to cover at least a preset area of the base substrate; arranging and aligning an open mask in association with the base substrate, wherein the open mask has at least one opening for vapor deposition, and the at least one shielding sheet is positioned corresponding to the at least one opening and each has an area that is less than an area of a corresponding opening to shield a portion of the corresponding opening, and wherein the portion of the corresponding opening is separate from a boundary of the corresponding opening; and evaporating to form an evaporation material layer on the base substrate, to which the shielding sheet is attached.

Method for preparing array substrate, display panel and evaporation apparatus

The present invention relates to the field of display technology, and discloses a method for preparing an array substrate, a display panel and an evaporation apparatus. A method for preparing an array substrate comprises: fixing a base substrate to an evaporation stage; attaching a shielding sheet to the base substrate to cover at least a preset area of the base substrate; arranging and aligning an open mask in association with the base substrate; and evaporating to form a evaporation material layer on the base substrate, to which the shielding sheet is attached, with the open mask.

In embodiments of the present disclosure, there is provided an assertion-based question answering manner. After a question and the related passage are obtained, an assertion answer to the question is determined based on content of the passage, and the assertion answer has a predetermined structure and represents a complete semantic meaning. Then, the assertion answer to the question may be outputted to the user. In the embodiments of the present disclosure, the question and the relevant passage are used as input, and a semi-structured assertion answer is output. The assertion answer according to embodiments of the present disclosure can provide richer semantic content than the traditional short answer, and provide a more concise expression than the traditional long answer, thereby ensuring accuracy of the answer while improving the user experience.

Assertion-based question answering

The present disclosure provides a display backplane, a method for preparing the same, and a display device. The display backplane includes a substrate, an electronic device and an alignment mark arranged on the substrate, and a filling layer, the filling layer being filled in at least a part of a recessed area located on a surface of the substrate away from the electronic device, and a minimum distance between an orthogonal projection of the at least part of the recessed area on the substrate and an orthogonal projection of the alignment mark on the substrate being less than 200 &#x3bc;m.

Display backplane, method for preparing the same, and display device

A temporal information integration dis-occlusion system and method for using historical data to reconstruct a virtual view containing an occluded area. Embodiments of the system and method use temporal information of the scene captured previously to obtain a total history. This total history is warped onto information captured by a camera at a current time in order to help reconstruct the dis-occluded areas. The historical data (or frames) from the total history match only a portion of the frames contained in the captured information. This warping yields warped history information. Warping is performed by using one of two embodiments to match points in an estimation of the current information to points in the captured information. Next, regions of current information are split using a classifier. The warped history information and the captured information then are merged to obtain an estimate for the current information and the reconstructed virtual view.

Recovering dis-occluded areas using temporal information integration

This invention is concerned with biocompatible magnetic nanocrystals highly soluble and dispersible in a physiological buffer, powder of biocompatible magnetic nanocrystals and nanocrystals bearing surface reactive N-hydroxysuccinimide ester moiety, and preparations thereof. The magnetic nanocrystals in powder form are highly soluble in a physiological buffer. The resultant aqueous colloidal solution presents long term stability in ambient conditions. Moreover, the carboxyl group on the surface of the magnetic nanocrystals can be converted to N-hydroxysuccinimide ester moiety in an organic solvent. The resultant powder of the magnetic nanocrystals carrying surface N-hydroxysuccinimide ester moiety is soluble and dispersible in an aqueous solution. Different types of biomolecules bearing amino group can covalently be attached to the magnetic nanocrystal simply by mixing them in aqueous solutions. Moreover, the powder of the magnetic nanocrystals bearing surface N-hydroxysuccinimide ester moiety retain reaction activity with biomolecule after long-term storage.

Biocompatible magnetic nanocrystal, powder of a biocompatible magnetic nanocrystal bearing a surface reactive group and preparations thereof

Growing community of inventors

Beijing, China

Shujie Liu