BK

Brian E. D. Kingsbury

IBM: 25 patents #4,217 of 70,183Top 7%
Microsoft: 2 patents #17,506 of 40,388Top 45%
II International Computer Science Institute: 1 patents #4 of 16Top 25%
OU Ohio State University: 1 patents #193 of 584Top 35%
Overall (All Time): #128,592 of 4,157,543Top 4%
29
Patents All Time

Issued Patents All Time

Showing 25 most recent of 29 patents

Patent #TitleCo-InventorsDate
12387717 Multi-speaker data augmentation for improved end-to-end automatic speech recognition Samuel Thomas, Hong-Kwang Kuo, George Andrei Saon 2025-08-12
12148419 Reducing exposure bias in machine learning training of sequence-to-sequence transducers Xiaodong Cui, George Andrei Saon, David C. Haws, Zoltan Tueske 2024-11-19
12136414 Integrating dialog history into end-to-end spoken language understanding systems Samuel Thomas, Jatin Ganhotra, Hong-Kwang Kuo, Sachindra Joshi, George Andrei Saon +1 more 2024-11-05
12119008 End-to-end integration of dialog history for spoken language understanding Samuel Thomas, Vishal Sunder, Hong-Kwang Kuo, Jatin Ganhotra, Eric Fosler-Lussier 2024-10-15
12046236 Training end-to-end spoken language understanding systems with unordered entities Hong-Kwang Kuo, Zoltan Tueske, Samuel Thomas, George Andrei Saon 2024-07-23
11929062 End-to-end spoken language understanding without full transcripts Hong-Kwang Kuo, Zoltan Tueske, Samuel Thomas, Yinghui Huang, Kartik Audhkhasi 2024-03-12
11914678 Input encoding for classifier generalization Hazar Yueksel, Kush R. Varshney 2024-02-27
11908458 Customization of recurrent neural network transducers for speech recognition Gakuto Kurata, George Andrei Saon 2024-02-20
11908454 Integrating text inputs for training and adapting neural network transducer ASR models Samuel Thomas, Hong-Kwang Kuo, George Andrei Saon, Gakuto Kurata 2024-02-20
11568858 Transliteration based data augmentation for training multilingual ASR acoustic models in low resource settings Samuel Thomas, Kartik Audhkhasi 2023-01-31
11158303 Soft-forgetting for connectionist temporal classification based automatic speech recognition Kartik Audhkhasi, George Andrei Saon, Zoltan Tueske, Michael A. Picheny 2021-10-26
10360901 Learning front-end speech recognition parameters within neural network training Tara N. Sainath, Abdel-rahman Samir Abdel-rahman Mohamed, Bhuvana Ramabhadran 2019-07-23
10056075 Systems and methods for accelerating hessian-free optimization for deep neural networks by implicit preconditioning and sampling Lior Horesh, Tara N. Sainath 2018-08-21
9824683 Data augmentation method based on stochastic feature mapping for automatic speech recognition Xiaodong Cui, Vaibhava Goel 2017-11-21
9734823 Method and system for efficient spoken term detection using confusion networks Hong-Kwang Kuo, Lidia Mangu, Hagen Soltau 2017-08-15
9721559 Data augmentation method based on stochastic feature mapping for automatic speech recognition Xiaodong Cui, Vaibhava Goel 2017-08-01
9704482 Method and system for order-free spoken term detection Lidia Mangu, Michael A. Picheny, George Andrei Saon 2017-07-11
9697830 Method and system for order-free spoken term detection Lidia Mangu, Michael A. Picheny, George Andrei Saon 2017-07-04
9640186 Deep scattering spectrum in acoustic modeling for speech recognition Petr Fousek, Vaibhava Goel, Etienne Marcheret, Shay Maymon, David Nahamoo +3 more 2017-05-02
9601109 Systems and methods for accelerating hessian-free optimization for deep neural networks by implicit preconditioning and sampling Lior Horesh, Tara N. Sainath 2017-03-21
9477753 Classifier-based system combination for spoken term detection Hong-Kwang Kuo, Lidia Mangu, Hagen Soltau 2016-10-25
9418334 Hybrid pre-training of deep belief networks Tara N. Sainath, Bhuvana Ramabhadran 2016-08-16
9390370 Training deep neural network acoustic models using distributed hessian-free optimization 2016-07-12
9378464 Discriminative learning via hierarchical transformations Sasha P. Caskey, Dimitri Kanevsky, Tara N. Sainath, George Andrei Saon 2016-06-28
9262724 Low-rank matrix factorization for deep belief network training with high-dimensional output targets Tara N. Sainath, Vikas Sindhwani 2016-02-16