Mountain View, CA, United States of America

Dongseong Hwang

This inventor holds 1 USPTO granted patent and 1 published patent application and 1 EPO patent. Top assignee: Google Inc.. Active years: 2025.

USPTO Granted Patents = 1 

% Patents Active = 100.0

 

Average Co-Inventor Count = 14.0

ph-index = 1


Company Filing History:


Years Active: 2025

Loading Chart...
Loading Chart...
1 patent (USPTO):Explore Patents

Title: The Innovations of Dongseong Hwang

Introduction

Dongseong Hwang is a prominent inventor based in Mountain View, CA. He has made significant contributions to the field of automated speech recognition (ASR). His innovative work has led to the development of a unique ASR model that enhances the efficiency and accuracy of speech recognition technologies.

Latest Patents

Dongseong Hwang holds a patent for a "Unified cascaded encoder ASR model for dynamic model sizes." This automated speech recognition model includes a first encoder, a second encoder, and two decoders. The first encoder processes a sequence of acoustic frames to generate a higher-order feature representation. The first decoder then uses this representation to create a probability distribution over potential speech recognition hypotheses. The second encoder further refines this representation, allowing for improved accuracy in speech recognition.

Career Highlights

Hwang is currently employed at Google Inc., where he continues to push the boundaries of speech recognition technology. His work is instrumental in developing systems that can adapt to various dynamic model sizes, making ASR more versatile and effective.

Collaborations

Dongseong Hwang collaborates with talented colleagues such as Shaojin Ding and Yangzhang He. Together, they contribute to advancements in speech recognition and related technologies.

Conclusion

Dongseong Hwang's innovative contributions to automated speech recognition exemplify the impact of dedicated inventors in the tech industry. His work not only enhances current technologies but also paves the way for future advancements in the field.

Profile summary based on public USPTO records.
Please report any incorrect information to [email protected]
Loading…