Dong-Sheng Yu
183Patents
19h-index
69Co-inventors
89Inventor score
Filing activity: Jan 8, 2002 → Aug 24, 2023
Most-cited inventions
| Patent | Title | Area | Cited by | Status |
|---|---|---|---|---|
| US8219406B2 | Speech-centric multimodal user interface design in mobile technology | Physics | 362 | Active |
| US7551546B2 | Dual-mode shared OFDM methods/transmitters, receivers and systems | Electricity | 188 | Active |
| US7042858B1 | Soft handoff for OFDM | Electricity | 140 | Expired |
| US7103325B1 | Adaptive modulation and coding | Electricity | 105 | Expired |
| US7508798B2 | Virtual mimo communication system | Electricity | 79 | Expired |
| US10249305B2 | Permutation invariant training for talker-independent multi-talker speech separation | Physics | 63 | Active |
| US8315225B2 | Aspects to support LTE-A downlink hi-order MIMO | Electricity | 52 | Active |
| US8526400B2 | Radio access system and method using OFDM and CDMA for broadband data transmission | Electricity | 50 | Active |
| US9477925B2 | Deep neural networks training for speech and pattern recognition | Physics | 42 | Active |
| US7634406B2 | System and method for identifying semantic intent from acoustic information | Physics | 39 | Active |
| US8700552B2 | Exploiting sparseness in training deep neural networks | Physics | 34 | Active |
| US9454958B2 | Exploiting heterogeneous data in deep neural network-based speech recognition systems | Physics | 28 | Active |
| US7773699B2 | Method and apparatus for channel quality measurements | Electricity | 27 | Active |
| US8019602B2 | Automatic speech recognition learning using user corrections | Physics | 23 | Active |
| US7856351B2 | Integrated speech recognition and semantic classification | Physics | 23 | Active |
| US7317680B2 | Channel mapping for OFDM | Electricity | 22 | Expired |
| US8718021B2 | Uplink control signal design for wireless system | Electricity | 21 | Active |
| US9374198B2 | Methods and systems for HARQ protocols | Electricity | 21 | Active |
| US9324321B2 | Low-footprint adaptation and personalization for a deep neural network | Physics | 19 | Active |
| US7394860B2 | Combined space-time decoding | Electricity | 18 | Expired |
| US8239195B2 | Adapting a compressed model for use in speech recognition | Physics | 18 | Active |
| US7864735B2 | Soft handoff for OFDM | Electricity | 17 | Active |
| US9842585B2 | Multilingual deep neural network | Physics | 16 | Active |
| US8527829B2 | Methods and systems for HARQ protocols | Electricity | 16 | Active |
| US9177550B2 | Conservatively adapting a deep neural network in a recognition system | Physics | 16 | Active |
Source: USPTO / EPO open patent data. Inventor disambiguation is heuristic; counts are objective bibliographic measures.