Jilong Wu

Title: Innovations of Jilong Wu

Introduction

Jilong Wu is an accomplished inventor based in Mountain View, CA. He has made significant contributions to the field of audio processing and keyword detection. With a total of 2 patents, his work has garnered attention in the tech industry.

Latest Patents

One of Jilong Wu's latest patents is focused on a method for small footprint multi-channel keyword spotting. This innovative method detects a hotword in a spoken utterance by receiving a sequence of input frames that characterize streaming multi-channel audio. Each channel of the audio includes respective audio features captured by separate dedicated microphones. The method processes these audio features in parallel using a three-dimensional (3D) single value decomposition filter (SVDF) input layer of a memorized neural network. It generates a corresponding multi-channel audio feature representation based on a concatenation of the respective audio features. Additionally, the method generates a probability score indicating the presence of a hotword in the audio. If the probability score meets a certain threshold, it initiates a wake-up process on a user device.

Career Highlights

Jilong Wu is currently employed at Google Inc., where he continues to innovate and develop new technologies. His work has been instrumental in advancing the capabilities of audio recognition systems.

Collaborations

Jilong Wu collaborates with Yiteng Huang, contributing to various projects and enhancing the development of audio processing technologies.

Conclusion

Jilong Wu's contributions to the field of audio processing and keyword detection highlight his innovative spirit and technical expertise. His patents reflect a commitment to advancing technology in meaningful ways.