| 12482483 |
Length perturbation techniques for improving generalization of deep neural network acoustic models |
Xiaodong Cui, Brian E. D. Kingsbury |
2025-11-25 |
|
| 12444405 |
Textual knowledge transfer for improved speech recognition and understanding |
Samuel Thomas, Vishal Sunder, Hong-Kwang Kuo, Brian E. D. Kingsbury, Eric Fosler-Lussier |
2025-10-14 |
|
| 12387717 |
Multi-speaker data augmentation for improved end-to-end automatic speech recognition |
Samuel Thomas, Hong-Kwang Kuo, Brian E. D. Kingsbury |
2025-08-12 |
|
| 12288551 |
Accuracy of streaming RNN transducer |
Gakuto Kurata |
2025-04-29 |
|
| 12148419 |
Reducing exposure bias in machine learning training of sequence-to-sequence transducers |
Xiaodong Cui, Brian E. D. Kingsbury, David C. Haws, Zoltan Tueske |
2024-11-19 |
$17,641,000 |
| 12136414 |
Integrating dialog history into end-to-end spoken language understanding systems |
Samuel Thomas, Jatin Ganhotra, Hong-Kwang Kuo, Sachindra Joshi, Zoltan Tueske +1 more |
2024-11-05 |
$24,022,000 |
| 12046236 |
Training end-to-end spoken language understanding systems with unordered entities |
Hong-Kwang Kuo, Zoltan Tueske, Samuel Thomas, Brian E. D. Kingsbury |
2024-07-23 |
$16,565,000 |
| 11942078 |
Chunking and overlap decoding strategy for streaming RNN transducers for speech recognition |
— |
2024-03-26 |
$9,065,000 |
| 11908454 |
Integrating text inputs for training and adapting neural network transducer ASR models |
Samuel Thomas, Hong-Kwang Kuo, Brian E. D. Kingsbury, Gakuto Kurata |
2024-02-20 |
$7,691,000 |
| 11908458 |
Customization of recurrent neural network transducers for speech recognition |
Gakuto Kurata, Brian E. D. Kingsbury |
2024-02-20 |
$7,691,000 |
| 11783811 |
Accuracy of streaming RNN transducer |
Gakuto Kurata |
2023-10-10 |
$6,086,000 |
| 11741946 |
Multiplicative integration in neural network transducer models for end-to-end speech recognition |
Daniel Bolanos |
2023-08-29 |
$6,011,000 |
| 11158303 |
Soft-forgetting for connectionist temporal classification based automatic speech recognition |
Kartik Audhkhasi, Zoltan Tueske, Brian E. D. Kingsbury, Michael A. Picheny |
2021-10-26 |
$2,874,000 |
| 11151996 |
Vocal recognition using generally available speech-to-text systems and user-defined vocal training |
Nicolò Sgobba, Antonello Izzi, Erik Rueger |
2021-10-19 |
$2,168,000 |
| 11120802 |
Diarization driven by the ASR based segmentation |
Kenneth W. Church, Dimitrios Dimitriadis, Petr Fousek, Miroslav Novak |
2021-09-14 |
$2,674,000 |
| 10902843 |
Using recurrent neural network for partitioning of audio data into segments that each correspond to a speech feature cluster identifier |
Dimitrios Dimitriadis, David C. Haws, Michael A. Picheny, Samuel Thomas |
2021-01-26 |
$1,788,000 |
| 10546575 |
Using recurrent neural network for partitioning of audio data into segments that each correspond to a speech feature cluster identifier |
Dimitrios Dimitriadis, David C. Haws, Michael A. Picheny, Samuel Thomas |
2020-01-28 |
$1,679,000 |
| 10468031 |
Diarization driven by meta-information identified in discussion content |
Kenneth W. Church, Dimitrios Dimitriadis, Petr Fousek, Miroslav Novak |
2019-11-05 |
$4,028,000 |
| 10262260 |
Method and system for joint training of hybrid neural networks for acoustic modeling in automatic speech recognition |
Hagen Soltau |
2019-04-16 |
$3,839,000 |
| 10249292 |
Using long short-term memory recurrent neural network for speaker diarization segmentation |
Dimitrios Dimitriadis, David C. Haws, Michael A. Picheny, Samuel Thomas |
2019-04-02 |
$2,364,000 |
| 9858919 |
Speaker adaptation of neural network acoustic models using I-vectors |
— |
2018-01-02 |
$1,907,000 |
| 9704482 |
Method and system for order-free spoken term detection |
Brian E. D. Kingsbury, Lidia Mangu, Michael A. Picheny |
2017-07-11 |
$1,748,000 |
| 9697830 |
Method and system for order-free spoken term detection |
Brian E. D. Kingsbury, Lidia Mangu, Michael A. Picheny |
2017-07-04 |
|
| 9665823 |
Method and system for joint training of hybrid neural networks for acoustic modeling in automatic speech recognition |
Hagen Soltau |
2017-05-30 |
$1,983,000 |
| 9378464 |
Discriminative learning via hierarchical transformations |
Sasha P. Caskey, Dimitri Kanevsky, Brian E. D. Kingsbury, Tara N. Sainath |
2016-06-28 |
$5,648,000 |
