Issued Patents All Time
Showing 25 most recent of 29 patents
| Patent # | Title | Co-Inventors | Date |
|---|---|---|---|
| 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 |