Inventor
YONGHUI WU
Inventor
US
Overview
Patents· 46 as inventor
Public. Assignee & technology derived from the patent record. Each patent links to its LexDana page.
G10Lprimary
G10LSpeech analysis techniques or speech synthesis37%
G06NComputing arrangements based on specific computational models32%
G06FElectric digital data processing17%
H04LTransmission of digital information, e.g. telegraphic communication3%
G02BOptical elements, systems or apparatus2%
H04WWireless communication networks2%
G06KGraphical data reading1%
G06TImage data processing or generation, in general1%
G06VImage or video recognition or understanding1%
H04NPictorial communication, e.g. television1%
PatentTitleYear
12,488,780Parallel tacotron non-autoregressive and controllable TTS202512,482,455Systems and methods for training dual-mode machine-learned speech recognition models202512,477,595Providing Wi-Fi protected setup (WPS) by sending a code to a network device using a phone202512,444,408Two-pass end to end speech recognition202512,443,806Machine translation using neural network models202512,400,633End-to-end speech waveform generation through data density gradient estimation202512,373,666Convolution-augmented transformer models202512,353,981Training of large neural networks202512,282,857Relative margin for contrastive learning202512,254,865Multi-dialect and multilingual speech recognition202512,249,315Unsupervised parallel tacotron non-autoregressive and controllable text-to-speech202512,222,994Quick application startup method and related apparatus202512,190,860End-to-end text-to-speech conversion202512,175,963Synthesis of speech from text in a voice of a target speaker using neural networks202412,170,667Fast access to local area network (LAN) graphical user interface (GUI) by client device202412,148,444Synthesizing speech from text using neural networks202412,112,198Asynchronous distributed data flow for machine learning workloads202412,106,749Speech recognition with sequence-to-sequence models202412,100,382Text-to-speech using duration prediction202412,094,453Fast emit low-latency streaming ASR with sequence-level emission regularization utilizing forward and backward probabilities between nodes of an alignment lattice202412,087,273Multilingual speech synthesis and cross-language voice cloning202412,079,703Convolution-augmented transformer models202412,047,445Application interface migration system and method, and related device202412,032,920Direct speech-to-speech translation via machine learning202412,020,685Phonemes and graphemes for neural text-to-speech202411,922,932Minimum word error rate training for attention-based sequence-to-sequence models202411,908,448Parallel tacotron non-autoregressive and controllable TTS202411,900,915Multi-dialect and multilingual speech recognition202411,862,142End-to-end text-to-speech conversion202411,848,002Synthesis of speech from text in a voice of a target speaker using neural networks202311,823,656Unsupervised parallel tacotron non-autoregressive and controllable text-to-speech202311,809,834Machine translation using neural network models202311,755,834Selective text prediction for electronic messaging202311,646,019Minimum word error rate training for attention-based sequence-to-sequence models202311,580,952Multilingual speech synthesis and cross-language voice cloning202311,556,381Asynchronous distributed data flow for machine learning workloads202311,488,575Synthesis of speech from text in a voice of a target speaker using neural networks202211,475,874Generating diverse and natural text-to-speech samples202211,475,706Fingerprint identification device, method and electronic device202211,468,244Large-scale multilingual speech recognition with a streaming end-to-end model202211,335,333Speech recognition with sequence-to-sequence models202211,335,321Building a text-to-speech system from a small amount of speech data202211,287,646Method for correcting an image, storage medium and projection device202211,238,845Multi-dialect and multilingual speech recognition202211,145,293Speech recognition with sequence-to-sequence models202111,138,392Machine translation using neural network models2021Career & activity timeline
Assembled from patent assignee/location history and declaration credentials.
2021–2025Patents assigned to GOOGLE LLC (40)· patent assignee history
2021–2025Based in US· patent location history
2022Patents assigned to SHENZHEN GOODIX TECH CO LTD (1)· patent assignee history
2022Patents assigned to XIAN ZHONGXING NEW SOFTWARE CO LTD (1)· patent assignee history
2022–2025Based in CN· patent location history
2024–2025Patents assigned to ARRIS ENTPR LLC (2)· patent assignee history
2024–2025Patents assigned to HUAWEI TECH CO LTD (2)· patent assignee history
Inventor activity
Assignee and location history derived from the patent record.
Assignees
| Assignee | Patents | Span |
|---|---|---|
| GOOGLE LLC | 40 | 2021–2025 |
| ARRIS ENTPR LLC | 2 | 2024–2025 |
| HUAWEI TECH CO LTD | 2 | 2024–2025 |
| SHENZHEN GOODIX TECH CO LTD | 1 | 2022 |
| XIAN ZHONGXING NEW SOFTWARE CO LTD | 1 | 2022 |
Locations
| Location | Patents | Span |
|---|---|---|
| US | 40 | 2021–2025 |
| CN | 6 | 2022–2025 |