Issued Patents All Time
Showing 26–50 of 56 patents
| Patent # | Title | Co-Inventors | Date |
|---|---|---|---|
| 11670283 | Duration informed attention network (DURIAN) for audio-visual synthesis | Heng Lu, Chengzhu Yu | 2023-06-06 |
| 11636848 | Token-wise training for attention based end-to-end speech recognition | Peidong Wang, Jia Cui, Chao Weng | 2023-04-25 |
| 11610060 | Automatic lexical sememe prediction system using lexical dictionaries | Kun Xu, Chao Weng, Chengzhu Yu | 2023-03-21 |
| 11551136 | N-best softmax smoothing for minimum bayes risk training of attention based sequence-to-sequence models | Chao Weng, Jia Cui, Guangsen Wang, Jun Wang, Chengzhu Yu +1 more | 2023-01-10 |
| 11468879 | Duration informed attention network for text-to-speech analysis | Chengzhu Yu, Heng Lu | 2022-10-11 |
| 11430431 | Learning singing from speech | Chengzhu Yu, Heng Lu, Chao Weng | 2022-08-30 |
| 11423906 | Multi-tap minimum variance distortionless response beamformer with neural networks for target speech separation | Yong Xu, Meng Yu, Shi-Xiong Zhang, Chao Weng, Jianming Liu | 2022-08-23 |
| 11410652 | Multi-look enhancement modeling and application for keyword spotting | Meng Yu | 2022-08-09 |
| 11380307 | All deep learning minimum variance distortionless response beamformer for speech separation and enhancement | Yong Xu, Meng Yu, Shi-Xiong Zhang | 2022-07-05 |
| 11302301 | Learnable speed control for speech synthesis | Chengzhu Yu | 2022-04-12 |
| 11295751 | Multi-band synchronized neural vocoder | Chengzhu Yu, Meng Yu, Heng Lu | 2022-04-05 |
| 11257481 | Multi-task training architecture and strategy for attention-based speech recognition system | Jia Cui, Chao Weng, Guangsen Wang, Jun Wang, Chengzhu Yu +1 more | 2022-02-22 |
| 11257480 | Unsupervised singing voice conversion with pitch adversarial network | Chengzhu Yu, Heng Lu, Chao Weng | 2022-02-22 |
| 11183168 | Singing voice conversion | Chengzhu Yu, Heng Lu, Chao Weng | 2021-11-23 |
| 11170167 | Automatic lexical sememe prediction system using lexical dictionaries | Kun Xu, Chao Weng, Chengzhu Yu | 2021-11-09 |
| 11151979 | Duration informed attention network (DURIAN) for audio-visual synthesis | Heng Lu, Chengzhu Yu | 2021-10-19 |
| 11138966 | Unsupervised automatic speech recognition | Jianshu Chen, Chengzhu Yu, Chih-Kuan Yeh | 2021-10-05 |
| 11128435 | Distributed and collaborative analytics of encrypted data using deep polynomial networks | Shixiong Zhang | 2021-09-21 |
| 11037547 | Token-wise training for attention based end-to-end speech recognition | Peidong Wang, Jia Cui, Chao Weng | 2021-06-15 |
| 11011154 | Enhancing hybrid self-attention structure with relative-position-aware bias for speech synthesis | Shan Yang, Heng Lu, Shiyin Kang | 2021-05-18 |
| 11004443 | Multistage curriculum training framework for acoustic-to-word speech recognition | Chengzhu Yu, Chao Weng, Jia Cui | 2021-05-11 |
| 10923117 | Best path change rate for unsupervised language model weight selection | Peidong Wang, Jia Cui, Chao Weng | 2021-02-16 |
| 10861441 | Large margin training for attention-based end-to-end speech recognition | Peidong Wang, Jia Cui, Chao Weng | 2020-12-08 |
| 10672382 | Input-feeding architecture for attention based end-to-end speech recognition | Chao Weng, Jia Cui, Guangsen Wang, Jun Wang, Chengzhu Yu +1 more | 2020-06-02 |
| 9824684 | Prediction-based sequence recognition | Yu Zhang, Michael L. Seltzer, James G. Droppo | 2017-11-21 |