Inventor · disambiguated record
Weiran Wang
Also filed as: WANG WEIRAN
11 granted patents·15 pending applications·31 citations·filing 2007–2025
85Inventor score
Files withGOOGLE LLC14KONINKLIJKE PHILIPS NV3AMAZON TECH INC2SALESFORCE COM INC2BEIJING WODONG TIANJUN INFORMATION TECHNOLOGY CO LTD1
Top patents by PatentIndex Score
26 records- 0189US10418957B1Audio event detectionAMAZON TECH INC·Filed 2018·Granted Sep 17, 2019·10 cites·17 claims
- 0287US10246817B2Treatment of a fabric articleKONINKLIJKE PHILIPS NV·Filed 2013·Granted Apr 2, 2019·6 cites·6 claims
- 0386US10803885B1Audio event detectionAMAZON TECH INC·Filed 2018·Granted Oct 13, 2020·7 cites·26 claims
- 0485US11328731B2Phone-based sub-word units for end-to-end speech recognitionSALESFORCE COM INC·Filed 2020·Granted May 10, 2022·2 cites·20 claims
- 0575US12198060B2Systems and methods for mutual information based self-supervised learningSALESFORCE COM INC·Filed 2020·Granted Jan 14, 2025·1 cites·20 claims
- 0672US2025308512A1Deliberation by text-only and semi-supervised trainingGOOGLE LLC·Filed 2025·Application pending·0 cites
- 0768US9739500B2Air purification apparatusKONINKLIJKE PHILIPS NV·Filed 2013·Granted Aug 22, 2017·5 cites·15 claims
- 0867US12354595B2Deliberation by text-only and semi-supervised trainingGOOGLE LLC·Filed 2023·Granted Jul 8, 2025·0 cites·20 claims
- 0959US2018172649A1Ph monitoring deviceKONINKLIJKE PHILIPS NV·Filed 2017·Application pending·0 cites
- 1055US2025378825A1Augmenting conformers with structured state-space sequence models for online speech recognitionGOOGLE LLC·Filed 2024·Application pending·0 cites
- 1153US12417770B2Unified cascaded encoder ASR model for dynamic model sizesGOOGLE LLC·Filed 2023·Granted Sep 16, 2025·0 cites·19 claims
- 1253US12190869B2Optimizing inference performance for conformerGOOGLE LLC·Filed 2022·Granted Jan 7, 2025·0 cites·18 claims
- 1353US2025078815A1Quantization and sparsity aware fine-tuning for speech recognition with universal speech modelsGOOGLE LLC·Filed 2024·Application pending·0 cites
- 1452US2024304181A1Connecting different asr application domains with speaker-tagsGOOGLE LLC·Filed 2024·Application pending·0 cites
- 1552US2024028829A1Joint Speech and Text Streaming Model for ASRGOOGLE LLC·Filed 2023·Application pending·0 cites
- 1652US2013220375A1Ph monitoring deviceSHI JUN·Filed 2011·Application pending·0 cites
- 1752US2024153495A1Multi-Output Decoders for Multi-Task Learning of ASR and Auxiliary TasksGOOGLE LLC·Filed 2023·Application pending·0 cites
- 1851US12354598B2Rare word recognition with LM-aware MWER trainingGOOGLE LLC·Filed 2023·Granted Jul 8, 2025·0 cites·24 claims
- 1951US12106022B2Method and device for simulating dynamic digital twin model of dominant operation of wind turbine generator assemblyUNIV NORTH CHINA ELECTRIC POWER·Filed 2023·Granted Oct 1, 2024·0 cites·9 claims
- 2051US2025118292A1Word-level end-to-end neural speaker diarization with auxnetGOOGLE LLC·Filed 2024·Application pending·0 cites
- 2151US2024296840A1Text Injection For Training Auxiliary Tasks In Speech Recognition ModelsGOOGLE LLC·Filed 2024·Application pending·0 cites
- 2249US2023107248A1Deliberation of Streaming RNN-Transducer by Non-Autoregressive DecodingGOOGLE LLC·Filed 2022·Application pending·0 cites
- 2348US2023099386A1System of recommending item, method of recommending item, computer system, and mediumBEIJING WODONG TIANJUN INFORMATION TECHNOLOGY CO LTD·Filed 2021·Application pending·0 cites
- 2444US2025252960A1Longform word-level end-to-end speaker diarization with dynamic audio cohortGOOGLE LLC·Filed 2025·Application pending·0 cites
- 2541US2009254932A1Inserting advertisements in a television programKONINKL PHILIPS ELECTRONICS NV·Filed 2007·Application pending·0 cites
- 2638US2015090673A1Apparatus and method for purifying liquidKONINK PHILPS N V·Filed 2013·Application pending·0 cites
Join the waitlist — get patent alerts
Get an alert when Weiran Wang files or is granted a new patent.
We store only your email — no account needed. See our privacy policy.
Identity basis: PatentsView inventor disambiguation (2025Q4-odp release). How scoring works →