logo

For the Inventor, By the Inventor

Saratoga, CA, United States of America

Mingqing Chen

This inventor holds 6 USPTO granted patents and 6 published patent applications and 2 EPO patents. Top assignee: Google Inc.. Active years: 2025-2026.

IDiyas Innovation Intelligence. (2026). Inventor Profile: Mingqing Chen. Retrieved from https://idiyas.com/inventor/mingqing-chen-yuzyhgg2

Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile

USPTO Granted Patents = 6 

% Patents Active = 100.0

 

Average Co-Inventor Count = 6.3

ph-index = 1


Company Filing History:

goldMedal6 out of 33,959 
 
Google Inc.
 patents

Years Active: 2025-2026

Loading Chart...
Loading Chart...
6 patents (USPTO):Explore Patents
1. 12762393 - Federated learning with partially trainable networks (2026-10-13),
2. 12664978 - Federated knowledge distillation on an encoder of a global ASR model and/or an encoder of a client ASR model (2026-06-23),
3. 12664977 - Fly parameter compression and decompression to facilitate forward and/or back propagation at clients during federated learning (2026-06-23),
4. 12586569 - Knowledge distillation with domain mismatch for speech recognition (2026-03-24),
5. 12524679 - System(s) and method(s) to reduce a transferable size of language model(s) to enable decentralized learning thereof (2026-01-13),
6. 12340799 - Identifying and correcting automatic speech recognition (ASR) misrecognitions in a decentralized manner (2025-06-24),

Title: The Innovations of Mingqing Chen

Introduction

Mingqing Chen is a notable inventor based in Saratoga, California. He has made significant contributions to the field of automatic speech recognition (ASR). His innovative work focuses on identifying and correcting ASR misrecognitions in a decentralized manner.

Latest Patents

Mingqing Chen holds a patent for a method that identifies and corrects ASR misrecognitions. The patent describes implementations where on-device processors of client devices generate predicted textual segments corresponding to spoken utterances. These processors can receive further input to modify the predicted segments and store them as candidate correction pairs. The system then transmits these pairs to a remote system, which can determine their accuracy and update a global ASR model accordingly.

Career Highlights

Mingqing Chen is currently employed at Google Inc., where he continues to develop innovative solutions in the realm of speech recognition technology. His work has the potential to enhance user experiences by improving the accuracy of ASR systems.

Collaborations

Mingqing collaborates with talented individuals such as Rajiv Mathews and Rohit Prakash Prabhavalkar. Their combined expertise contributes to the advancement of ASR technologies.

Conclusion

Mingqing Chen's contributions to automatic speech recognition demonstrate his commitment to innovation and technology. His work not only addresses current challenges in ASR but also paves the way for future advancements in the field.

Profile summary based on public USPTO records.
Data Sources: USPTO Patent Grant XML, Patent Center, EPO & CIPO • Normalized by IDiyas Innovation Graph. Methodology & provenance architecturePlease report any incorrect information to [email protected]
Loading…