Inventor · disambiguated record
Zhehuai Chen
Also filed as: CHEN ZHEHUAI
11 granted patents·10 pending applications·14 citations·filing 2016–2025
84Inventor score
Top patents by PatentIndex Score
21 records- 0194US11222620B2Speech recognition using unspoken text and speech synthesisGOOGLE LLC·Filed 2020·Granted Jan 11, 2022·5 cites·30 claims
- 0291US12159617B2Injecting text in self-supervised speech pre-trainingGOOGLE LLC·Filed 2022·Granted Dec 3, 2024·2 cites·24 claims
- 0389US12272363B2Advancing the use of text and speech in ASR pretraining with consistency and contrastive lossesGOOGLE LLC·Filed 2022·Granted Apr 8, 2025·2 cites·22 claims
- 0488US11837216B2Speech recognition using unspoken text and speech synthesisGOOGLE LLC·Filed 2023·Granted Dec 5, 2023·1 cites·20 claims
- 0587US11929060B2Consistency prediction on streaming sequence modelsGOOGLE LLC·Filed 2021·Granted Mar 12, 2024·2 cites·26 claims
- 0683US11990117B2Using speech recognition to improve cross-language speech synthesisGOOGLE LLC·Filed 2021·Granted May 21, 2024·1 cites·20 claims
- 0783US11605368B2Speech recognition using unspoken text and speech synthesisGOOGLE LLC·Filed 2021·Granted Mar 14, 2023·1 cites·20 claims
- 0875US2024282292A1Using speech recognition to improve cross-language speech synthesisGOOGLE LLC·Filed 2024·Application pending·0 cites
- 0972US2025078807A1Injecting Text in Self-Supervised Speech Pre-trainingGOOGLE LLC·Filed 2024·Application pending·0 cites
- 1069US2025285609A1Conformer-based Speech Conversion ModelGOOGLE LLC·Filed 2025·Application pending·0 cites
- 1166US12400638B2Using aligned text and speech representations to train automatic speech recognition models without transcribed speech dataGOOGLE LLC·Filed 2023·Granted Aug 26, 2025·0 cites·24 claims
- 1261US12272348B2Conformer-based speech conversion modelGOOGLE LLC·Filed 2022·Granted Apr 8, 2025·0 cites·18 claims
- 1357US12512095B2Unsupervised data selection via discrete speech representation for automatic speech recognitionGOOGLE LLC·Filed 2023·Granted Dec 30, 2025·0 cites·18 claims
- 1454US12230249B2Supervised and unsupervised training with contrastive loss over sequencesGOOGLE LLC·Filed 2022·Granted Feb 18, 2025·0 cites·18 claims
- 1552US2024028829A1Joint Speech and Text Streaming Model for ASRGOOGLE LLC·Filed 2023·Application pending·0 cites
- 1651US2024153484A1Massive multilingual speech-text joint semi-supervised learning for text-to-speechGOOGLE LLC·Filed 2023·Application pending·0 cites
- 1751US2024304178A1Using text-injection to recognize speech without transcriptionGOOGLE LLC·Filed 2024·Application pending·0 cites
- 1849US2025166614A1Supervised and Unsupervised Training with Contrastive Loss Over SequencesGOOGLE LLC·Filed 2025·Application pending·0 cites
- 1948US2025095652A1Speech-to-text processing assisted with language models for conversational ai systems and applicationsNVIDIA CORP·Filed 2024·Application pending·0 cites
- 2045US2025078827A1Pronunciation-aware embedding generation for conversational ai systems and applicationsNVIDIA CORP·Filed 2024·Application pending·0 cites
- 2134US2019057685A1Method and Device for Speech Recognition DecodingAISPEECH CO LTD·Filed 2016·Application pending·0 cites
Join the waitlist — get patent alerts
Get an alert when Zhehuai Chen 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 →