This inventor holds 1 USPTO granted patent and 3 published patent applications. Top assignee: Nvidia Corporation. Active years: 2026.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
Company Filing History:
Years Active: 2026
Title: Junjie Lai: Inventor in Audio-Driven Facial Animation.
Introduction
Junjie Lai is an inventor based in Beijing, China, and works at NVIDIA Corporation. His patent work includes a machine-learning technique for generating facial animation from audio.
Latest Patents
Lai is associated with 1 patent: “Audio-Driven Facial Animation with Adaptive Speech Rate.” The invention detects when speech in an audio segment exceeds a threshold, then upsamples audio-related features to create a differently sized feature set. One or more machine-learning models use at least some of those features to generate facial animation corresponding to the audio.
Career Highlights
Lai’s listed patent reflects work at the intersection of audio processing, machine learning, and facial animation. The technique adapts its processing to faster speech, supporting the generation of corresponding animated facial output.
Collaborations
Lai’s listed coworkers include Zhengyu Huang and Dmitry Korobchenko.
Conclusion
Junjie Lai’s patent describes an adaptive, audio-driven approach to facial animation, connecting speech analysis with machine-learning-based visual output.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile