Issued Patents All Time
Showing 25 most recent of 39 patents
| Patent # | Title | Co-Inventors | Date |
|---|---|---|---|
| 12334059 | Contrastive Siamese network for semi-supervised speech recognition | Jaeyoung Kim, Soheil Khorram, Anshuman Tripathi, Han Lu, Qian Zhang | 2025-06-17 |
| 12315499 | Semi-supervised training scheme for speech recognition | Soheil Khorram, Anshuman Tripathi, Kim Jaeyoung, Han Lu, Qian Zhang | 2025-05-27 |
| 12266347 | End-to-end multi-talker overlapping speech recognition | Anshuman Tripathi, Han Lu | 2025-04-01 |
| 12254869 | One model unifying streaming and non-streaming speech recognition | Anshuman Tripathi, Han Lu, Qian Zhang, Jaeyoung Kim | 2025-03-18 |
| 12057124 | Reducing streaming ASR model delay with self alignment | Jaeyoung Kim, Han Lu, Anshuman Tripathi, Qian Zhang | 2024-08-06 |
| 11996088 | Setting latency constraints for acoustic models | Andrew W. Senior, Kanury Kanishka Rao | 2024-05-28 |
| 11961515 | Contrastive Siamese network for semi-supervised speech recognition | Jaeyoung Kim, Soheil Khorram, Anshuman Tripathi, Han Lu, Qian Zhang | 2024-04-16 |
| 11776531 | Encoder-decoder models for sequence to sequence mapping | Sean Matthew Shannon | 2023-10-03 |
| 11769493 | Training acoustic models using connectionist temporal classification | Kanury Kanishka Rao, Andrew W. Senior | 2023-09-26 |
| 11741947 | Transformer transducer: one model unifying streaming and non-streaming speech recognition | Anshuman Tripathi, Han Lu, Qian Zhang, Jaeyoung Kim | 2023-08-29 |
| 11721327 | Generating representations of acoustic sequences | Andrew W. Senior | 2023-08-08 |
| 11715486 | Convolutional, long short-term memory, fully connected deep neural networks | Tara N. Sainath, Andrew W. Senior, Oriol Vinyals | 2023-08-01 |
| 11521595 | End-to-end multi-talker overlapping speech recognition | Anshuman Tripathi, Han Lu | 2022-12-06 |
| 11341958 | Training acoustic models using connectionist temporal classification | Kanury Kanishka Rao, Andrew W. Senior | 2022-05-24 |
| 10923112 | Generating representations of acoustic sequences | Andrew W. Senior | 2021-02-16 |
| 10803855 | Training acoustic models using connectionist temporal classification | Kanury Kanishka Rao, Andrew W. Senior | 2020-10-13 |
| 10783900 | Convolutional, long short-term memory, fully connected deep neural networks | Tara N. Sainath, Andrew W. Senior, Oriol Vinyals | 2020-09-22 |
| 10733979 | Latency constraints for acoustic modeling | Andrew W. Senior, Kanury Kanishka Rao | 2020-08-04 |
| 10706840 | Encoder-decoder models for sequence to sequence mapping | Sean Matthew Shannon | 2020-07-07 |
| 10535338 | Generating representations of acoustic sequences | Andrew W. Senior | 2020-01-14 |
| 10431206 | Multi-accent speech recognition | Kanury Kanishka Rao | 2019-10-01 |
| 10325602 | Neural networks for speaker verification | Ignacio Lopez Moreno, Alan Sean Papir, Li Wan, Quan Wang | 2019-06-18 |
| 10275704 | Generating representations of input sequences using neural networks | Kanury Kanishka Rao, Fuchun Peng, Francoise Beaufays | 2019-04-30 |
| 10229672 | Training acoustic models using connectionist temporal classification | Kanury Kanishka Rao, Andrew W. Senior | 2019-03-12 |
| 10192556 | Speech recognition with acoustic models | Andrew W. Senior | 2019-01-29 |