John R. Hershey
42Patents
9h-index
39Co-inventors
75Inventor score
Filing activity: Jun 27, 2003 → Jul 26, 2023
Most-cited inventions
| Patent | Title | Area | Cited by | Status |
|---|---|---|---|---|
| US9368110B1 | Method for distinguishing components of an acoustic signal | Physics | 57 | Active |
| US7460160B2 | Multispectral digital camera employing both visible light and non-visible light sensing on a single image sensor | Electricity | 50 | Active |
| US7518631B2 | Audio-visual control system | Physics | 47 | Active |
| US9685155B2 | Method for distinguishing components of signal of environment | Physics | 26 | Active |
| US9881631B2 | Method for enhancing audio signal using phase information | Physics | 20 | Active |
| US9842106B2 | Method and system for role dependent context sensitive spoken and textual language understanding with neural networks | Physics | 17 | Active |
| US7689413B2 | Speech detection and enhancement using audio/video fusion | Physics | 11 | Active |
| US7664643B2 | System and method for speech separation and multi-talker speech recognition | Physics | 10 | Active |
| US7269560B2 | Speech detection and enhancement using audio/video fusion | Physics | 9 | Expired |
| US9069798B2 | Method of text classification using discriminative topic transformation | Physics | 9 | Active |
| US9582753B2 | Neural networks for transforming signals | Physics | 9 | Active |
| US10811000B2 | Methods and systems for recognizing simultaneous speech by multiple speakers | Physics | 8 | Active |
| US10176799B2 | Method and system for training language models to reduce recognition errors | Physics | 5 | Active |
| US10672388B2 | Method and apparatus for open-vocabulary end-to-end speech recognition | Physics | 5 | Active |
| US9477895B2 | Method and system for detecting events in an acoustic signal subject to cyclo-stationary noise | Physics | 5 | Active |
| US7596494B2 | Method and apparatus for high resolution speech reconstruction | Physics | 4 | Expired |
| US10593321B2 | Method and apparatus for multi-lingual end-to-end speech recognition | Physics | 4 | Active |
| US10417498B2 | Method and system for multi-modal fusion model | Electricity | 4 | Active |
| US9434389B2 | Actions prediction for hypothetical driving conditions | Performing Operations; Transporting | 4 | Active |
| US7486815B2 | Method and apparatus for scene learning and three-dimensional tracking using stereo video cameras | Physics | 4 | Active |
| US9251250B2 | Method and apparatus for processing text with variations in vocabulary usage | Physics | 4 | Active |
| US10529349B2 | Methods and systems for end-to-end speech separation with unfolded iterative phase reconstruction | Physics | 3 | Active |
| US9048942B2 | Method and system for reducing interference and noise in speech signals | Electricity | 3 | Active |
| US9679559B2 | Source signal separation by discriminatively-trained non-negative matrix factorization | Physics | 2 | Active |
| US11133011B2 | System and method for multichannel end-to-end speech recognition | Physics | 2 | Active |
Source: USPTO / EPO open patent data. Inventor disambiguation is heuristic; counts are objective bibliographic measures.