Issued Patents All Time
Showing 25 most recent of 95 patents
| Patent # | Title | Co-Inventors | Date |
|---|---|---|---|
| 12205596 | Generating and using text-to-speech data for speech recognition models | Guoli Ye, Yan Huang, Wenning Wei, Lei He, Eva Sharma +6 more | 2025-01-21 |
| 12141080 | Communication method, related computing system and storage medium for selecting a communication channel between modules | Jiangming JIN | 2024-11-12 |
| 12086704 | Machine learning model with depth processing units | Jinyu Li, Liang Lu, Changliang Liu | 2024-09-10 |
| 12014728 | Dynamic combination of acoustic model states | Kshitiz Kumar | 2024-06-18 |
| 11915686 | Speaker adaptation for attention-based encoder-decoder | Zhong Meng, Yashesh GAUR, Jinyu Li | 2024-02-27 |
| 11862144 | Augmented training data for end-to-end models | Rui Zhao, Jinyu Li | 2024-01-02 |
| 11823702 | Condition-invariant feature extraction network | Zhong Meng, Yong Zhao, Jinyu Li | 2023-11-21 |
| 11798535 | On-device custom wake word detection | Emilian Stoimenov, Rui Zhao, Kaustubh Kalgaonkar, Ivaylo Andreanov Enchev, Khuram Shahid +4 more | 2023-10-24 |
| 11790891 | Wake word selection assistance architectures and methods | Emilian Stoimenov, Khuram Shahid, Guoli Ye, Hosam A. Khalil | 2023-10-17 |
| 11776548 | Convolutional neural network with phonetic attention for speaker verification | Yong Zhao, Tianyan Zhou, Jinyu Li, Jian Wu, Zhuo Chen | 2023-10-03 |
| 11735190 | Attentive adversarial domain-invariant training | Zhong Meng, Jinyu Li | 2023-08-22 |
| 11705117 | Adaptive batching to reduce recognition latency | Hosam A. Khalil, Emilian Stoimenov, Chaojun Liu, Christopher Hakan BASOGLU, Amit Agarwal +2 more | 2023-07-18 |
| 11676006 | Universal acoustic modeling using neural mixture models | Amit Das, Jinyu Li, Changliang Liu | 2023-06-13 |
| 11657799 | Pre-training with alignments for recurrent neural network transducer based end-to-end speech recognition | Rui Zhao, Jinyu Li, Liang Lu, Hu Hu | 2023-05-23 |
| 11631399 | Layer trajectory long short-term memory with future context | Jinyu Li, Vadim Mazalov, Changliang Liu, Liang Lu | 2023-04-18 |
| 11620992 | Automated speech recognition confidence classifier | Kshitiz Kumar, Anastasios Anastasakos | 2023-04-04 |
| 11586930 | Conditional teacher-student learning for model training | Zhong Meng, Jinyu Li, Yong Zhao | 2023-02-21 |
| 11587569 | Generating and using text-to-speech data for speech recognition models | Guoli Ye, Yan Huang, Wenning Wei, Lei He, Eva Sharma +6 more | 2023-02-21 |
| 11563784 | Caption assisted calling to maintain connection in challenging network conditions | Akash Alok Mahajan | 2023-01-24 |
| 11562745 | Sequence-to-sequence speech recognition with latency threshold | Yashesh GAUR, Jinyu Li, Liang Lu, Hirofumi INAGUMA | 2023-01-24 |
| 11527238 | Internal language model for E2E models | Zhong Meng, Sarangarajan Parthasarathy, Xie Sun, Yashesh GAUR, Naoyuki KANDA +4 more | 2022-12-13 |
| 11429860 | Learning student DNN via output distribution | Jinyu Li, Rui Zhao, Jui-Ting Huang | 2022-08-30 |
| 11276410 | Convolutional neural network with phonetic attention for speaker verification | Yong Zhao, Tianyan Zhou, Jinyu Li, Jian Wu, Zhuo Chen | 2022-03-15 |
| 11244673 | Streaming contextual unidirectional models | Jinyu Li, Amit Agarwal, Harini Kesavamoorthy, Changliang Liu, Liang Lu | 2022-02-08 |
| 11232782 | Speaker adaptation for attention-based encoder-decoder | Zhong Meng, Yashesh GAUR, Jinyu Li | 2022-01-25 |