David Grangier
15Patents
6h-index
26Co-inventors
62Inventor score
Filing activity: Sep 18, 2009 → Sep 7, 2023
Most-cited inventions
| Patent | Title | Area | Cited by | Status |
|---|---|---|---|---|
| US8359282B2 | Supervised semantic indexing and its extensions | Physics | 14 | Active |
| US9489373B2 | Interactive segment extraction in computer-human interactive learning | Electricity | 10 | Active |
| US9779081B2 | Feature completion in computer-human interactive learning | Electricity | 9 | Active |
| US9355088B2 | Feature completion in computer-human interactive learning | Electricity | 8 | Active |
| US10372815B2 | Interactive concept editing in computer-human interactive learning | Electricity | 6 | Active |
| US9430460B2 | Active featuring in computer-human interactive learning | Electricity | 6 | Active |
| US8341095B2 | Supervised semantic indexing and its extensions | Physics | 5 | Active |
| US8706668B2 | Feature set embedding for incomplete data | Physics | 4 | Active |
| US9886669B2 | Interactive visualization of machine-learning performance | Physics | 4 | Active |
| US11023677B2 | Interactive feature selection for training a machine learning system and displaying discrepancies within the context of the document | Electricity | 3 | Active |
| US12236970B2 | Separating speech by source in audio recordings by predicting isolated audio signals conditioned on speaker representations | Physics | 0 | Active |
| US10839790B2 | Sequence-to-sequence convolutional architecture | Physics | 0 | Active |
| US11475909B2 | Separating speech by source in audio recordings by predicting isolated audio signals conditioned on speaker representations | Physics | 0 | Active |
| US11887623B2 | End-to-end speech diarization via iterative speaker embedding | Physics | 0 | Active |
| US12020138B2 | Generating audio using auto-regressive generative neural networks | Physics | 0 | Active |
Source: USPTO / EPO open patent data. Inventor disambiguation is heuristic; counts are objective bibliographic measures.