Yonghui Wu
58Patents
5h-index
156Co-inventors
71Inventor score
Filing activity: Jul 23, 2009 → Sep 27, 2024
Most-cited inventions
| Patent | Title | Area | Cited by | Status |
|---|---|---|---|---|
| US8060497B1 | Framework for evaluating web search scoring functions | Physics | 47 | Active |
| US8346792B1 | Query generation using structural similarity between documents | Physics | 32 | Active |
| US10713593B2 | Implicit bridging of machine learning tasks | Physics | 8 | Active |
| US8572075B1 | Framework for evaluating web search scoring functions | Physics | 8 | Active |
| US11646019B2 | Minimum word error rate training for attention-based sequence-to-sequence models | Physics | 5 | Active |
| US11145293B2 | Speech recognition with sequence-to-sequence models | Physics | 5 | Active |
| US11107463B2 | Minimum word error rate training for attention-based sequence-to-sequence models | Physics | 5 | Active |
| US11238845B2 | Multi-dialect and multilingual speech recognition | Physics | 4 | Active |
| US9436747B1 | Query generation using structural similarity between documents | Physics | 4 | Active |
| US11048910B2 | Fingerprint identification device, method and electronic device | Physics | 4 | Active |
| US9208232B1 | Generating synthetic descriptive text | Physics | 4 | Active |
| US11900915B2 | Multi-dialect and multilingual speech recognition | Physics | 4 | Active |
| US9584369B2 | Methods of representing software defined networking-based multiple layer network topology views | Electricity | 3 | Active |
| US11335333B2 | Speech recognition with sequence-to-sequence models | Physics | 3 | Active |
| US10573293B2 | End-to-end text-to-speech conversion | Physics | 3 | Active |
| US11138392B2 | Machine translation using neural network models | Physics | 3 | Active |
| US11475706B2 | Fingerprint identification device, method and electronic device | Physics | 2 | Active |
| US10248662B2 | Generating descriptive text for images in documents using seed descriptors | Physics | 2 | Active |
| US11468244B2 | Large-scale multilingual speech recognition with a streaming end-to-end model | Physics | 1 | Active |
| US11580952B2 | Multilingual speech synthesis and cross-language voice cloning | Physics | 1 | Active |
| US11809834B2 | Machine translation using neural network models | Physics | 1 | Active |
| US10971170B2 | Synthesizing speech from text using neural networks | Physics | 1 | Active |
| US11755834B2 | Selective text prediction for electronic messaging | Physics | 1 | Active |
| US11488575B2 | Synthesis of speech from text in a voice of a target speaker using neural networks | Physics | 1 | Active |
| US9092479B1 | Query generation using structural similarity between documents | Physics | 1 | Active |
Source: USPTO / EPO open patent data. Inventor disambiguation is heuristic; counts are objective bibliographic measures.