Issued Patents 2025
Showing 1–4 of 4 patents
| Patent # | Title | Co-Inventors | Date |
|---|---|---|---|
| 12400638 | Using aligned text and speech representations to train automatic speech recognition models without transcribed speech data | Zhehuai Chen, Ankur Bapna, Yu Zhang, Bhuvana Ramabhadran | 2025-08-26 |
| 12272363 | Advancing the use of text and speech in ASR pretraining with consistency and contrastive losses | Zhehuai Chen, Bhuvana Ramabhadran, Pedro J. Moreno Mengibar, Yuan-Fang Wang, Yu Zhang | 2025-04-08 |
| 12230249 | Supervised and unsupervised training with contrastive loss over sequences | Bhuvana Ramabhadran, Zhehuai Chen, Yuan-Fang Wang, Yu Zhang, Jesse Emond | 2025-02-18 |
| 12190862 | Using non-parallel voice conversion for speech conversion models | Gary Wang, Bhuvana Ramabhadran, Fadi Biadsy | 2025-01-07 |