Inventor · disambiguated record
Yanzhang He
Also filed as: HE YANZHANG
18 granted patents·12 pending applications·32 citations·filing 2019–2025
90Inventor score
Files withGOOGLE LLC30
Top patents by PatentIndex Score
30 records- 0193US11610586B2Learning word-level confidence for subword end-to-end automatic speech recognitionGOOGLE LLC·Filed 2021·Granted Mar 21, 2023·6 cites·28 claims
- 0293US11568878B2Voice shortcut detection with speaker verificationGOOGLE LLC·Filed 2021·Granted Jan 31, 2023·6 cites·20 claims
- 0391US11948570B2Key phrase spottingGOOGLE LLC·Filed 2022·Granted Apr 2, 2024·2 cites·20 claims
- 0491US11295739B2Key phrase spottingGOOGLE LLC·Filed 2019·Granted Apr 5, 2022·12 cites·15 claims
- 0589US11715458B2Efficient streaming non-recurrent on-device end-to-end modelGOOGLE LLC·Filed 2021·Granted Aug 1, 2023·2 cites·20 claims
- 0689US11594212B2Attention-based joint acoustic and text on-device end-to-end modelGOOGLE LLC·Filed 2021·Granted Feb 28, 2023·2 cites·21 claims
- 0783US12374323B24-bit conformer with accurate quantization training for speech recognitionGOOGLE LLC·Filed 2023·Granted Jul 29, 2025·2 cites·20 claims
- 0876US2024420687A1Two-pass end to end speech recognitionGOOGLE LLC·Filed 2024·Application pending·0 cites
- 0973US12051404B2Efficient streaming non-recurrent on-device end-to-end modelGOOGLE LLC·Filed 2023·Granted Jul 30, 2024·0 cites·20 claims
- 1073US2024371363A1Efficient streaming non-recurrent on-device end-to-end modelGOOGLE LLC·Filed 2024·Application pending·0 cites
- 1172US2025308512A1Deliberation by text-only and semi-supervised trainingGOOGLE LLC·Filed 2025·Application pending·0 cites
- 1272US2024221750A1Key phrase spottingGOOGLE LLC·Filed 2024·Application pending·0 cites
- 1372US2024363122A1Voice shortcut detection with speaker verificationGOOGLE LLC·Filed 2024·Application pending·0 cites
- 1471US2023186901A1Attention-Based Joint Acoustic and Text On-Device End-to-End ModelGOOGLE LLC·Filed 2023·Application pending·0 cites
- 1570US2025329333A1Optimizing personal vad for on-device speech recognitionGOOGLE LLC·Filed 2025·Application pending·0 cites
- 1670US2025029624A1Joint Acoustic Echo Cancelation, Speech Enhancement, and Voice Separation for Automatic Speech RecognitionGOOGLE LLC·Filed 2024·Application pending·0 cites
- 1769US12033641B2Voice shortcut detection with speaker verificationGOOGLE LLC·Filed 2023·Granted Jul 9, 2024·0 cites·20 claims
- 1869US2025095634A1Language Agnostic Multilingual End-To-End Streaming On-Device ASR SystemGOOGLE LLC·Filed 2024·Application pending·0 cites
- 1967US12354595B2Deliberation by text-only and semi-supervised trainingGOOGLE LLC·Filed 2023·Granted Jul 8, 2025·0 cites·20 claims
- 2063US12347438B2Optimizing personal VAD for on-device speech recognitionGOOGLE LLC·Filed 2023·Granted Jul 1, 2025·0 cites·20 claims
- 2163US12073824B2Two-pass end to end speech recognitionGOOGLE LLC·Filed 2020·Granted Aug 27, 2024·0 cites·14 claims
- 2261US12183322B2Language agnostic multilingual end-to-end streaming on-device ASR systemGOOGLE LLC·Filed 2022·Granted Dec 31, 2024·0 cites·20 claims
- 2360US12119014B2Joint acoustic echo cancelation, speech enhancement, and voice separation for automatic speech recognitionGOOGLE LLC·Filed 2021·Granted Oct 15, 2024·0 cites·24 claims
- 2458US12444408B2Two-pass end to end speech recognitionGOOGLE LLC·Filed 2020·Granted Oct 14, 2025·0 cites·18 claims
- 2555US12424206B2Context-aware neural confidence estimation for rare word speech recognitionGOOGLE LLC·Filed 2023·Granted Sep 23, 2025·0 cites·20 claims
- 2655US2024347043A1Robustness Aware Norm Decay for Quantization Aware Training and GeneralizationGOOGLE LLC·Filed 2024·Application pending·0 cites
- 2754US12094453B2Fast emit low-latency streaming ASR with sequence-level emission regularization utilizing forward and backward probabilities between nodes of an alignment latticeGOOGLE LLC·Filed 2021·Granted Sep 17, 2024·0 cites·24 claims
- 2853US2025078815A1Quantization and sparsity aware fine-tuning for speech recognition with universal speech modelsGOOGLE LLC·Filed 2024·Application pending·0 cites
- 2952US2024153495A1Multi-Output Decoders for Multi-Task Learning of ASR and Auxiliary TasksGOOGLE LLC·Filed 2023·Application pending·0 cites
- 3044US12456460B2Multi-task learning for end-to-end automated speech recognition confidence and deletion estimationGOOGLE LLC·Filed 2021·Granted Oct 28, 2025·0 cites·24 claims
Join the waitlist — get patent alerts
Get an alert when Yanzhang He 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 →