Issued Patents All Time
Showing 25 most recent of 142 patents
| Patent # | Title | Co-Inventors | Date |
|---|---|---|---|
| 12417770 | Unified cascaded encoder ASR model for dynamic model sizes | Shaojin Ding, Yangzhang He, Xin Wang, Weiran Wang, Trevor Strohman +8 more | 2025-09-16 |
| 12412566 | Lookup-table recurrent language model | Ronny Huang, Trevor Strohman, Shankar Kumar | 2025-09-09 |
| 12361927 | Emitting word timings with end-to-end models | Basilio Garcia Castillo, David Rybach, Trevor Strohman, Ruoming Pang | 2025-07-15 |
| 12354598 | Rare word recognition with LM-aware MWER training | Weiran Wang, Tongzhou Chen, Ehsan Variani, Rohit Prakash Prabhavalkar, Ronny Huang +7 more | 2025-07-08 |
| 12354595 | Deliberation by text-only and semi-supervised training | Ke Hu, Yanzhang He, Rohit Prakash Prabhavalkar, Sepand Mavandadi, Weiran Wang +1 more | 2025-07-08 |
| 12354597 | Disfluency detection models for natural conversational voice systems | Shuo-yiin Chang, Bo Li, Trevor Strohman, Chao Zhang | 2025-07-08 |
| 12322383 | Predicting word boundaries for on-device batching of end-to-end speech recognition models | Shaan Jagdeep Patrick Bijwadia, Jiahui Yu, Shuo-yiin Chang, Yangzhang He | 2025-06-03 |
| 12315497 | Intended query detection using E2E modeling for continued conversation | Shuo-yiin Chang, Guru Prakash Arumugam, Zelin Wu, Bo Li, Qiao Liang +4 more | 2025-05-27 |
| 12254865 | Multi-dialect and multilingual speech recognition | Zhifeng Chen, Bo Li, Eugene Weinstein, Yonghui Wu, Pedro J. Moreno Mengibar +3 more | 2025-03-18 |
| 12249317 | Joint unsupervised and supervised training for multilingual ASR | Bo Li, Junwen Bai, Yu Zhang, Ankur Bapna, Nikhil Siddhartha +1 more | 2025-03-11 |
| 12211509 | Fusion of acoustic and text representations in RNN-T | Chao Zhang, Bo Li, Zhiyun Lu, Shuo-yiin Chang | 2025-01-28 |
| 12190869 | Optimizing inference performance for conformer | Rami Botros, Anmol Gulati, Krzysztof Marcin Choromanski, Ruoming Pang, Trevor Strohman +2 more | 2025-01-07 |
| 12183322 | Language agnostic multilingual end-to-end streaming on-device ASR system | Bo Li, Ruoming Pang, Shuo-yiin Chang, Qiumin Xu, Trevor Strohman +6 more | 2024-12-31 |
| 12154581 | Cascaded encoders for simplified streaming and non-streaming ASR | Arun Narayanan, Chung-Cheng Chiu, Ruoming Pang, Rohit Prakash Prabhavalkar, Jiahui Yu +2 more | 2024-11-26 |
| 12118988 | Transducer-based streaming deliberation for cascaded encoders | Ke Hu, Arun Narayanan, Ruoming Pang, Trevor Strohman | 2024-10-15 |
| 12106749 | Speech recognition with sequence-to-sequence models | Rohit Prakash Prabhavalkar, Zhifeng Chen, Bo Li, Chung-Cheng Chiu, Kanury Kanishka Rao +8 more | 2024-10-01 |
| 12094453 | Fast emit low-latency streaming ASR with sequence-level emission regularization utilizing forward and backward probabilities between nodes of an alignment lattice | Jiahui Yu, Chung-Cheng Chiu, Bo Li, Shuo-yiin Chang, Wei Han +5 more | 2024-09-17 |
| 12073824 | Two-pass end to end speech recognition | Yanzhang He, Bo Li, Arun Narayanan, Ruoming Pang, Antoine Jean Bruguier +2 more | 2024-08-27 |
| 12062363 | Tied and reduced RNN-T | Rami Botros | 2024-08-13 |
| 12051407 | Contextual biasing for speech recognition | Rohit Prakash Prabhavalkar, Golan Pundak | 2024-07-30 |
| 12051404 | Efficient streaming non-recurrent on-device end-to-end model | Arun Narayanan, Rami Botros, Yanzhang He, Ehsan Variani, Cyril Georges Luc Allauzen +3 more | 2024-07-30 |
| 12027158 | Deliberation model-based two-pass end-to-end speech recognition | Ke Hu, Ruoming Pang, Rohit Prakash Prabhavalkar | 2024-07-02 |
| 12027154 | Emitting word timings with end-to-end models | Basilio Garcia Castillo, David Rybach, Trevor Strohman, Ruoming Pang | 2024-07-02 |
| 12014725 | Large-scale language model data selection for rare-word speech recognition | Ronny Huang | 2024-06-18 |
| 11942076 | Phoneme-based contextualization for cross-lingual speech recognition in end-to-end models | Ke Hu, Golan Pundak, Rohit Prakash Prabhavalkar, Antoine Jean Bruguier | 2024-03-26 |