Jinsong Zheng

Title: Jinsong Zheng: Innovator in Automatic Speech Recognition

Introduction

Jinsong Zheng is a notable inventor based in Edison, NJ (US). He has made significant contributions to the field of automatic speech recognition. His innovative work has led to the development of a patented method that enhances the accuracy and robustness of speech detection.

Latest Patents

Jinsong Zheng holds a patent titled "Method and apparatus for performing real-time endpoint detection in automatic speech recognition." This invention involves a method and apparatus designed for real-time endpoint detection. A filter is applied to the input speech signal, and the output of this filter is evaluated using a state transition diagram, specifically a finite state machine. The design of the filter is optimized based on several criteria to improve detection accuracy. The state transition diagram consists of three states, allowing for effective endpoint detection that can be applied to energy normalization of the speech portion of the signal.

Career Highlights

Jinsong Zheng is associated with Lucent Technologies Inc., where he has contributed to advancements in speech recognition technology. His work has been instrumental in developing methods that enhance the performance of automatic speech recognition systems.

Collaborations

Throughout his career, Jinsong Zheng has collaborated with esteemed colleagues, including Chin-Hui Lee and Qi P Li. These collaborations have further enriched his research and development efforts in the field.

Conclusion

Jinsong Zheng's innovative contributions to automatic speech recognition demonstrate his expertise and commitment to advancing technology. His patented methods continue to influence the field, showcasing the importance of innovation in enhancing communication technologies.