Issued Patents 2023
Showing 1–13 of 13 patents
| Patent # | Title | Co-Inventors | Date |
|---|---|---|---|
| 11783849 | Enhanced multi-channel acoustic models | Ehsan Variani, Kevin William Wilson, Ron J. Weiss, Arun Narayanan | 2023-10-10 |
| 11756534 | Adaptive audio enhancement for multichannel speech recognition | Bo Li, Ron J. Weiss, Michiel A. U. Bacchiani, Kevin William Wilson | 2023-09-12 |
| 11749259 | Proper noun recognition in end-to-end speech recognition | Charles Caleb Peyser, Golan Pundak | 2023-09-05 |
| 11741366 | Compressed recurrent neural network models | Vikas Sindhwani | 2023-08-29 |
| 11727920 | Tied and reduced RNN-T | Rami Botros | 2023-08-15 |
| 11715458 | Efficient streaming non-recurrent on-device end-to-end model | Arun Narayanan, Rami Botros, Yanzhang He, Ehsan Variani, Cyril Georges Luc Allauzen +3 more | 2023-08-01 |
| 11715486 | Convolutional, long short-term memory, fully connected deep neural networks | Andrew W. Senior, Oriol Vinyals, Hasim Sak | 2023-08-01 |
| 11664021 | Contextual biasing for speech recognition | Rohit Prakash Prabhavalkar, Golan Pundak, Antoine Jean Bruguier | 2023-05-30 |
| 11646019 | Minimum word error rate training for attention-based sequence-to-sequence models | Rohit Prakash Prabhavalkar, Yonghui Wu, Patrick Nguyen, Zhifeng Chen, Chung-Cheng Chiu +1 more | 2023-05-09 |
| 11610586 | Learning word-level confidence for subword end-to-end automatic speech recognition | David Qiu, Qiujia Li, Yanzhang He, Yu Zhang, Bo Li +6 more | 2023-03-21 |
| 11594212 | Attention-based joint acoustic and text on-device end-to-end model | Ruoming Pang, Ron J. Weiss, Yanzhang He, Chung-Cheng Chiu, Trevor Strohman | 2023-02-28 |
| 11580956 | Emitting word timings with end-to-end models | Basi Garcia, David Rybach, Trevor Strohman, Ruoming Pang | 2023-02-14 |
| 11545142 | Using context information with end-to-end models for speech recognition | Ding Zhao, Bo Li, Ruoming Pang, David Rybach, Deepti Bhatia +1 more | 2023-01-03 |