Issued Patents 2025
Showing 1–7 of 7 patents
| Patent # | Title | Co-Inventors | Date |
|---|---|---|---|
| 12400638 | Using aligned text and speech representations to train automatic speech recognition models without transcribed speech data | Andrew Rosenberg, Zhehuai Chen, Ankur Bapna, Yu Zhang | 2025-08-26 |
| 12354598 | Rare word recognition with LM-aware MWER training | Weiran Wang, Tongzhou Chen, Tara N. Sainath, Ehsan Variani, Rohit Prakash Prabhavalkar +7 more | 2025-07-08 |
| 12272348 | Conformer-based speech conversion model | Zhehuai Chen, Fadi Biadsy, Pedro J. Moreno Mengibar | 2025-04-08 |
| 12272363 | Advancing the use of text and speech in ASR pretraining with consistency and contrastive losses | Andrew Rosenberg, Zhehuai Chen, Pedro J. Moreno Mengibar, Yuan-Fang Wang, Yu Zhang | 2025-04-08 |
| 12254875 | Multilingual re-scoring models for automatic speech recognition | Neeraj Gaur, Tongzhou Chen, Ehsan Variani, Parisa Haghani, Pedro J. Moreno Mengibar | 2025-03-18 |
| 12230249 | Supervised and unsupervised training with contrastive loss over sequences | Andrew Rosenberg, Zhehuai Chen, Yuan-Fang Wang, Yu Zhang, Jesse Emond | 2025-02-18 |
| 12190862 | Using non-parallel voice conversion for speech conversion models | Andrew Rosenberg, Gary Wang, Fadi Biadsy | 2025-01-07 |