Jundai Sun

Title: Jundai Sun: Innovator in Speech Source Separation Technology

Introduction

Jundai Sun is a notable inventor based in Beijing, China. He has made significant contributions to the field of speech processing, particularly through his innovative patent related to speech source separation.

Latest Patents

Jundai Sun holds a patent titled "Method and apparatus for speech source separation based on a convolutional neural network." This patent describes a method for Convolutional Neural Network (CNN) based speech source separation. The method includes several steps: providing multiple frames of a time-frequency transform of an original noisy speech signal, inputting this transform into an aggregated multi-scale CNN with parallel convolution paths, extracting features from the input, obtaining an aggregated output, and generating an output mask for extracting speech from the original noisy signal. Additionally, the patent outlines an apparatus for CNN-based speech source separation and a computer program product that includes instructions for executing the method.

Career Highlights

Jundai Sun is currently employed at Dolby Laboratories Licensing Corporation, where he continues to advance his research and development in audio technologies. His work at Dolby has allowed him to apply his innovative ideas in a practical setting, contributing to the company's reputation for excellence in sound technology.

Collaborations

Jundai has collaborated with notable colleagues, including Zhiwei Shuang and Lie Lu. Their combined expertise in the field has fostered a productive environment for innovation and development.

Conclusion

Jundai Sun's contributions to speech processing through his patented technology exemplify the impact of innovation in the field. His work not only enhances audio quality but also showcases the potential of convolutional neural networks in practical applications.