Inventor profile of:

Dong Yu

City:

Bothell, Washington

Country:

United States

Published Applications:

67

Last publication date:

2025-07-24

Top Assignees for applications by Dong Yu

The entities that hold a legal rights for patent applications filed by inventor Yu Dong:

Recent patent applications by Yu Dong

Dong Yu from Bothell, US has applied for patents for these inventions. The list has both pending applications and granted patents:

#1 | 2025-07-24
US20250238693A1
Physics

MOE MODEL FROM BLOCK SPARSE COMPUTATION'S POINT OF VIEW

#2 | 2024-06-27
US20240211689A1
Physics

Extractive method for speaker identification in texts with self-training

#3 | 2023-06-22
US20230196087A1
Physics

INSTANCE ADAPTIVE TRAINING WITH NOISE ROBUST LOSSES AGAINST NOISY LABELS

#4 | 2023-04-27
US20230132090A1
Physics

Bridging semantics between words and definitions via aligning word sense inventories

#5 | 2023-03-23
US20230092440A1
Physics

N-best softmax smoothing for minimum bayes risk training of attention based sequence-to-sequence models

#6 | 2023-02-16
US20230053148A1
Physics

Extractive method for speaker identification in texts with self-training

#7 | 2022-10-27
US20220343904A1
Physics

Learning singing from speech

#8 | 2022-09-29
US20220310092A1
Physics

Multi-look enhancement modeling and application for keyword spotting

#9 | 2022-06-16
US20220189495A1
Physics

Multi-band synchronized neural vocoder

#10 | 2022-06-09
US20220180856A1
Physics

Learnable speed control of speech synthesis

#11 | 2022-04-14
US20220115005A1
Physics

Multi-task training architecture and strategy for attention-based speech recognition system

#12 | 2022-02-03
US20220036874A1
Physics

Singing voice conversion

#13 | 2022-01-27
US20220027567A1
Physics

Automatic lexical sememe prediction system using lexical dictionaries

#14 | 2022-01-13
US20220013123A1
Physics

Multi-tap minimum variance distortionless response beamformer with neural networks for target speech separation

#15 | 2022-01-06
US20220005468A1
Physics

Multi-look enhancement modeling and application for keyword spotting

#16 | 2021-12-16
US20210390970A1
Physics

Multi-modal framework for multi-channel target speech separation

#17 | 2021-12-02
US20210375259A1
Physics

Duration informed attention network (DURIAN) for audio-visual synthesis

#18 | 2021-09-09
US20210280165A1
Physics

Unsupervised singing voice conversion with pitch adversarial network

#19 | 2021-09-09
US20210280164A1
Physics

Learnable speed control for speech synthesis

#20 | 2021-08-26
US20210264901A1
Physics

Token-wise training for attention based end-to-end speech recognition

#21 | 2021-08-19
US20210256958A1
Physics

Singing voice conversion

#22 | 2021-08-12
US20210248997A1
Physics

Learning singing from speech

#23 | 2021-07-29
US20210233513A1
Physics

Audio recognition method and system and machine device

#24 | 2021-05-20
US20210152751A1
Electricity

Model training method, media information synthesis method, and related apparatuses

#25 | 2021-03-25
US20210090584A1
Physics

Multi-band synchronized neural vocoder

#26 | 2021-02-25
US20210056949A1
Physics

Duration informed attention network (DURIAN) for audio-visual synthesis

#27 | 2021-02-11
US20210043190A1
Physics

Speech recognition method and apparatus, and method and apparatus for training speech recognition model

#28 | 2021-01-14
US20210014039A1
Electricity

Distributed and collaborative analytics of encrypted data using deep polynomial networks

#29 | 2021-01-07
US20210005216A1
Physics

Multi-person speech separation method and apparatus using a generative adversarial network model

#30 | 2020-11-26
US20200372905A1
Physics

Mixed speech recognition method and apparatus, and computer-readable storage medium

#31 | 2020-10-29
US20200342849A1
Physics

Duration informed attention network for text-to-speech analysis

#32 | 2020-10-01
US20200311196A1
Physics

Automatic lexical sememe prediction system using lexical dictionaries

#33 | 2020-08-20
US20200265833A1
Physics

Best path change rate for unsupervised language model weight selection

#34 | 2020-08-20
US20200265831A1
Physics

Large margin training for attention-based end-to-end speech recognition

#35 | 2020-08-20
US20200265830A1
Physics

Token-wise training for attention based end-to-end speech recognition

#36 | 2020-08-13
US20200258497A1
Physics

Unsupervised automatic speech recognition

#37 | 2020-08-13
US20200258496A1
Physics

Enhancing hybrid self-attention structure with relative-position-aware bias for speech synthesis

#38 | 2020-05-14
US20200151623A1
Physics

N-best softmax smoothing for minimum bayes risk training of attention based sequence-to-sequence models

#39 | 2020-04-30
US20200135174A1
Physics

Multi-task training architecture and strategy for attention-based speech recognition system

#40 | 2020-04-16
US20200118547A1
Physics

Input-feeding architecture for attention based end-to-end speech recognition

#41 | 2020-03-05
US20200074983A1
Physics

Multistage curriculum training framework for acoustic-to-word speech recognition

#42 | 2020-02-06
US20200043467A1
Physics

Monaural multi-talker speech recognition with attention mechanism and gated convolutional networks

#43 | 2019-10-03
US20190304438A1
Physics

Adaptive permutation invariant training with auxiliary information for monaural multi-talker speech recognition

#44 | 2019-10-03
US20190304437A1
Physics

Knowledge transfer in permutation invariant training for single-channel multi-talker speech recognition

#45 | 2019-06-27
US20190198024A1
Physics

Permutation invariant training for talker-independent multi-talker speech separation

#46 | 2018-09-06
US20180254040A1
Physics

Multi-talker speech recognizer

#47 | 2018-05-03
US20180121814A1
Physics

HYPERPARAMETER TUNING

#48 | 2018-03-01
US20180060728A1
Physics

Deep Embedding Forest: Forest-based Serving with Deep Embedding Features

#49 | 2017-11-23
US20170337924A1
Physics

Permutation invariant training for talker-independent multi-talker speech separation

#50 | 2017-10-26
US20170308789A1
Physics

Computing system for training neural networks

#51 | 2017-08-17
US20170236056A1
Physics

Automated predictive modeling and framework

#52 | 2017-06-22
US20170178666A1
Physics

Multi-speaker speech separation

#53 | 2017-04-20
US20170110120A1
Physics

Mixed speech recognition

#54 | 2016-09-29
US20160284348A1
Physics

Mixed speech recognition

#55 | 2016-05-19
US20160140956A1
Physics

Prediction-based sequence recognition

#56 | 2016-01-28
US20160026914A1
Physics

Discriminative pretraining of deep neural networks

#57 | 2015-09-24
US20150269933A1
Physics

Mixed speech recognition

#58 | 2015-09-10
US20150255061A1
Physics

Low-footprint adaptation and personalization for a deep neural network

#59 | 2014-09-11
US20140257805A1
Physics

Multilingual deep neural network

#60 | 2014-09-11
US20140257804A1
Physics

Exploiting heterogeneous data in deep neural network-based speech recognition systems

#61 | 2014-09-11
US20140257803A1
Physics

Conservatively adapting a deep neural network in a recognition system

#62 | 2014-05-22
US20140142929A1
Physics

Deep neural networks training for speech and pattern recognition

#63 | 2014-03-06
US20140067735A1
Physics

Computer-implemented deep tensor neural network

#64 | 2013-08-15
US20130212052A1
Physics

Tensor deep stacked neural network

#65 | 2013-05-30
US20130138589A1
Physics

Exploiting sparseness in training deep neural networks

#66 | 2013-05-30
US20130138436A1
Physics

Discriminative pretraining of deep neural networks

#67 | 2012-11-29
US20120303565A1
Physics

Learning processes for single hidden layer neural networks with linear output units

InventorID:

393680 ⎘