Baltimore, MD, United States of America

Xuankai Chang

This inventor holds 3 USPTO granted patents and 1 published patent application. Top assignee: Microsoft Technology Licensing, LLC. Active years: 2023-2025.

USPTO Granted Patents = 3 

% Patents Active = 100.0

Average Co-Inventor Count = 6.0

ph-index = 1


Company Filing History:


Years Active: 2023-2025

Loading Chart...
3 patents (USPTO):Explore Patents

Title: Xuankai Chang: Innovator in Speech Recognition Technology

Introduction

Xuankai Chang is a prominent inventor based in Baltimore, MD (US). He has made significant contributions to the field of speech recognition technology, holding a total of 3 patents. His work focuses on enhancing the accuracy and efficiency of automatic speech recognition systems.

Latest Patents

One of Xuankai Chang's latest patents is a "Hypothesis stitcher for speech recognition of long-form audio." This innovative technology provides superior performance, including higher accuracy and reduced computational cost. The disclosed operation involves segmenting an audio stream into multiple segments, identifying speakers within those segments, and performing automatic speech recognition (ASR) to generate short-segment hypotheses. These hypotheses are then merged into a consolidated hypothesis set, incorporating stitching symbols for improved accuracy. The patent also outlines various operational variations, including alignment-based and serialized stitchers, which can function as speaker-specific or multi-speaker stitchers.

Career Highlights

Xuankai Chang is currently employed at Microsoft Technology Licensing, LLC, where he continues to develop cutting-edge technologies in speech recognition. His work has been instrumental in advancing the capabilities of ASR systems, making them more efficient and reliable.

Collaborations

He collaborates with talented individuals such as Naoyuki Kanda and Yashesh Gaur, contributing to a dynamic team focused on innovation in technology.

Conclusion

Xuankai Chang's contributions to speech recognition technology exemplify the impact of innovative thinking in the field. His patents reflect a commitment to enhancing the performance of automatic speech recognition systems, paving the way for future advancements.

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